MCP Radar
MCP Server

mcp

io.datadef/mcp
Data & Analytics Design & Creative Developer Tools Public & reachable MCP 2025-11-25

What this MCP does

Creates and edits data architecture diagrams with tables, data flows, column lineage, grouping, validation, and PNG export.

Capabilities

Tools

39 tools
canvas_add_flow_arrow
Add a flow arrow
When: Use after the final layout, where one arrow should stand for a bundle of identical flows (zone to zone). Draw one large labelled arrow SHAPE between two areas of the diagram — "ingest", "serve", "publish". It is a drawing, not a connection: it links nothing and moves with nothing. To connect nodes use canvas_connect_nodes; never replace existing edges with this. Position it in the gap between the two areas using canvas_measure_canvas. Batch: `arrows` (up to 12) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'arrows'], 'properties': {'arrows': {'type': 'array', 'items': {'type': 'object', 'required': ['label', 'x', 'y'], 'properties': {'x': {'type': 'number', 'description': "Absolute x of the arrow's top-left corner."}, 'y': {'type': 'number', 'description': "Absolute y of the arrow's top-left corner."}, 'color': {'type': 'string', 'description': 'Colour name or hex. Default a soft grey-blue.'}, 'label': {'type': 'string', 'minLength': 1, 'description': 'What moves, e.g. "batch + streaming ingest".'}, 'width': {'type': 'number', 'maximum': 4000, 'minimum': 40, 'description': 'Length. Default 200.'}, 'direction': {'enum': ['right', 'left', 'up', 'down'], 'type': 'string', 'description': 'Which way the head points. Default right.'}, 'thickness': {'type': 'number', 'maximum': 400, 'minimum': 12, 'description': 'How thick the arrow body is. Default 48. Big flows deserve 60-120.'}}, 'additionalProperties': False}, 'maxItems': 12, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_add_lineage
Record column lineage
When: Use to record which source columns produce which target columns. No line is drawn. Record column-level lineage: which source column produces which target column, and how. This is what makes the diagram queryable for impact analysis, so add it for every real transformation. canvas_remove_lineage undoes it. Batch: `links` (up to 100) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_validate_canvas before you finish.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'links'], 'properties': {'links': {'type': 'array', 'items': {'type': 'object', 'required': ['sourceNode', 'targetNode'], 'properties': {'joinType': {'type': 'string', 'description': 'direct, transform, aggregation, lookup, filter, union, or a join kind.'}, 'sourceNode': {'type': 'string', 'description': 'Upstream node id or label.'}, 'targetNode': {'type': 'string', 'description': 'Downstream node id or label.'}, 'description': {'type': 'string', 'description': 'The transformation logic in one line.'}, 'sourceColumn': {'type': 'string', 'description': 'Upstream column name. Omit for table-level lineage.'}, 'targetColumn': {'type': 'string', 'description': 'Downstream column name.'}}, 'additionalProperties': False}, 'maxItems': 100, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_add_nodes
Add nodes
When: Use to add components (tables, pipelines, sources, consumers, service icons), each placed in its zone with `group`. Add one or more nodes to the canvas. Batch every node you want in a single call. Positions are assigned by canvas_layout_canvas afterwards — never set them yourself. Batch: `nodes` (up to 40) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. If you have not already, call get_design_guide first: it carries Datadef's size, edge and zone standard, and diagrams built without it read poorly. Next: canvas_connect_nodes for the real flows, then canvas_layout_canvas once when the structure is complete.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'nodes'], 'properties': {'nodes': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'label'], 'properties': {'icon': {'type': 'string', 'description': 'Icon id from search_icons, e.g. "snowflake". A product name is resolved if unambiguous; an unknown one is left out.'}, 'type': {'enum': ['table', 'kpi', 'dataSource', 'pipeline', 'consumption', 'serviceIcon'], 'type': 'string', 'description': 'table = a dataset with columns; dataSource = an external system feeding data in; pipeline = a job that moves or transforms data; consumption = a dashboard, app, or ML model reading data; kpi = a business metric; serviceIcon = a plain labelled service logo (needs an icon).'}, 'group': {'type': 'string', 'description': 'Zone id or label to place this node in. The zone must already exist.'}, 'label': {'type': 'string', 'description': 'Display name. Use the real object name, e.g. "fct_orders".'}, 'family': {'enum': ['source', 'ingest', 'bronze', 'silver', 'gold', 'consume', 'dbt', 'neutral'], 'type': 'string', 'description': 'Accent hue for the node tile. Tables infer their layer from names; set this for operators/endpoints or to override.'}, 'columns': {'type': 'array', 'items': {'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Column name, e.g. "customer_id".'}, 'type': {'type': 'string', 'description': 'SQL type, e.g. "varchar", "bigint", "timestamp". Default "unknown" for a new column; an existing column keeps its type.'}, 'description': {'type': 'string', 'description': 'What the column means in business terms.'}, 'isForeignKey': {'type': 'boolean'}, 'isPrimaryKey': {'type': 'boolean'}}, 'additionalProperties': False}, 'description': 'Columns. Table nodes only.'}, 'kpiUnit': {'type': 'string'}, 'schedule': {'type': 'string', 'description': 'Cron expression or cadence, e.g. "0 2 * * *".'}, 'dataOwner': {'type': 'string'}, 'kpiTarget': {'type': 'string'}, 'kpiFormula': {'type': 'string'}, 'technology': {'type': 'string', 'description': 'Implementing tool, e.g. "dbt", "Airflow".'}, 'dataSteward': {'type': 'string'}, 'description': {'type': 'string', 'description': 'One line on what this is and why it exists.'}, 'pipelineType': {'type': 'string', 'description': 'etl, elt, transformation, streaming, batch, cdc, or reverse_etl.'}, 'teamInCharge': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}, 'maxItems': 40, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_add_region
Add a region
When: Use after the final layout to mark nodes that belong together without moving them into a zone. Regions do not move with layout. Draw a labelled translucent area behind existing nodes to show they belong together, without reparenting them. Use this when the grouping is a reading aid rather than real containment, when areas would need to overlap, or when a node belongs to two ideas at once — canvas_group_nodes cannot express any of those because it moves nodes into the zone. Call canvas_measure_canvas first and size the region to enclose the nodes with roughly 24px of margin. Batch: `regions` (up to 12) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'regions'], 'properties': {'regions': {'type': 'array', 'items': {'type': 'object', 'required': ['label', 'x', 'y', 'width', 'height'], 'properties': {'x': {'type': 'number'}, 'y': {'type': 'number'}, 'color': {'type': 'string', 'description': 'Colour name or hex, drawn translucent. Default a neutral slate.'}, 'label': {'type': 'string', 'minLength': 1, 'description': 'Region name, drawn at the top-left.'}, 'width': {'type': 'number', 'maximum': 6000, 'minimum': 60}, 'height': {'type': 'number', 'maximum': 6000, 'minimum': 60}}, 'additionalProperties': False}, 'maxItems': 12, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_add_shape
Add a shape
When: Use rarely: a pointer or highlight the user asked for. Never as a backdrop; zones are the containers. Place a rectangle, circle, arrow, or line as a visual annotation — a divider, a highlight. Shapes are drawings: they connect nothing (use canvas_connect_nodes for arrows between nodes) and they are not zones (use canvas_group_nodes). Batch: `shapes` (up to 20) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'shapes'], 'properties': {'shapes': {'type': 'array', 'items': {'type': 'object', 'required': ['shape', 'x', 'y'], 'properties': {'x': {'type': 'number'}, 'y': {'type': 'number'}, 'label': {'type': 'string', 'description': 'Text drawn on the shape.'}, 'shape': {'enum': ['rectangle', 'circle', 'arrow', 'line'], 'type': 'string'}, 'width': {'type': 'number', 'maximum': 4000, 'minimum': 4}, 'height': {'type': 'number', 'maximum': 4000, 'minimum': 1}, 'fillColor': {'type': 'string', 'description': 'Colour name or hex.'}, 'strokeColor': {'type': 'string', 'description': 'Colour name or hex.'}}, 'additionalProperties': False}, 'maxItems': 20, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_add_standalone_node
Add one node at a fixed spot
When: Use only when the user wants a node at a specific position, outside the automatic layout. Otherwise use canvas_add_nodes. Add a single data node at an exact position, without connecting it to anything. Use when the user wants something placed somewhere specific, or when you will wire it up yourself afterwards. For building out a connected diagram, canvas_add_nodes is better — it batches and lets layout position everything. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'type', 'label'], 'properties': {'x': {'type': 'number', 'description': 'Absolute x. Omit to place clear of the existing diagram.'}, 'y': {'type': 'number', 'description': 'Absolute y.'}, 'icon': {'type': 'string', 'description': 'Icon id from search_icons.'}, 'type': {'enum': ['table', 'kpi', 'dataSource', 'pipeline', 'consumption', 'serviceIcon'], 'type': 'string'}, 'label': {'type': 'string'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'technology': {'type': 'string'}, 'description': {'type': 'string'}}, 'additionalProperties': False}
canvas_add_text
Add a note
When: Use for a note that tells the diagram's reader a decision, constraint or gotcha. Pass `anchor` (the node or zone it explains) and it is placed beside it, no coordinates needed. To edit a note's text use canvas_update_nodes. Add a text note: a caption, a callout, a note explaining a decision. Give `anchor` (the node or zone it explains) and the note is placed beside it, clear of other content, without coordinates. Use x/y only for a note that belongs to no particular element. Notes are annotations: they take no edges. To change an existing note's text use canvas_update_nodes. Batch: `texts` (up to 20) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'texts'], 'properties': {'texts': {'type': 'array', 'items': {'type': 'object', 'required': ['text'], 'properties': {'x': {'type': 'number', 'description': 'Absolute x of the top-left corner, when there is no anchor.'}, 'y': {'type': 'number', 'description': 'Absolute y of the top-left corner, when there is no anchor.'}, 'bold': {'type': 'boolean'}, 'text': {'type': 'string', 'minLength': 1, 'description': 'The text content. Newlines are preserved.'}, 'style': {'enum': ['note', 'callout', 'caption'], 'type': 'string', 'description': 'note = quiet grey text (default), callout = highlighted amber box, caption = small bold label.'}, 'width': {'type': 'number', 'maximum': 1200, 'minimum': 40, 'description': 'Default 220 (240 for anchored notes).'}, 'anchor': {'type': 'string', 'description': 'Node or zone id or label this note explains; the note is placed next to it.'}, 'height': {'type': 'number', 'maximum': 800, 'minimum': 20, 'description': 'Default 60.'}, 'fontSize': {'type': 'number', 'maximum': 72, 'minimum': 8, 'description': 'Default 14.'}, 'textColor': {'type': 'string', 'description': 'Colour name or hex, e.g. "#111827".'}, 'transparent': {'type': 'boolean', 'description': 'Draw with no box or border, for a caption floating over the canvas.'}}, 'additionalProperties': False}, 'maxItems': 20, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_align_nodes
Align nodes by hand
When: Use only when the user asked for alignment that layout does not give. Align nodes to a shared edge or centre line, or space them evenly. Cleaner and far more reliable than computing coordinates by hand. Batch: `nodes` (up to 40) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'nodes', 'mode'], 'properties': {'mode': {'enum': ['left', 'right', 'top', 'bottom', 'center-horizontal', 'center-vertical', 'distribute-horizontal', 'distribute-vertical'], 'type': 'string', 'description': 'left/right/top/bottom align edges; center-* align centre lines; distribute-* space evenly between the outermost two.'}, 'nodes': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 40, 'minItems': 2, 'description': 'Node ids or labels.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_batch
Apply several canvas changes at once
When: use whenever you would otherwise make several canvas_* write calls in a row, above all with tools that take one item per call: create every zone (group_nodes), convert many nodes (replace_node), set several tables' columns (set_columns). Eighteen zone creations or thirty-five replacements become one call and one save. Each operation is {"tool": "<canvas tool, with or without the canvas_ prefix>", "args": {<that tool's arguments, without diagram_id>}}. Operations run in order on the same diagram, so a later one can use what an earlier one created by its exact label (create a zone in operation 1, add nodes with that zone as their group in operation 2). All or nothing: if one operation fails, nothing is saved and the result names the failing operation. Write tools only; read with canvas_view. Returns compact JSON: one line per operation, the ids created, changed or removed, and the new revision. Next: canvas_layout_canvas once if the structure changed (or end the batch with a layout_canvas operation), then canvas_view.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'operations'], 'properties': {'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'operations': {'type': 'array', 'items': {'type': 'object', 'required': ['tool'], 'properties': {'args': {'type': 'object', 'description': "That tool's arguments, exactly as its own canvas_* tool takes them, without diagram_id.", 'additionalProperties': {}}, 'tool': {'type': 'string', 'description': 'A canvas write tool, e.g. "group_nodes", "add_nodes", "replace_node", "set_columns", "connect_nodes", "layout_canvas".'}}, 'additionalProperties': False}, 'maxItems': 50, 'minItems': 1, 'description': 'Applied in order, all or nothing. Up to 50.'}}, 'additionalProperties': False}
canvas_collapse_nodes
Collapse nodes into one
When: Use to merge several similar nodes into one while keeping their connections, usually after canvas_suggest_simplifications. Merge several nodes into one summary node, keeping every connection. Use when a set of near-identical objects adds length without adding meaning — eight staging models that all behave the same become "stg_* (8)". Do not use when the individual objects are what the reader came for. Batch: `nodes` (up to 40) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_layout_canvas once, then canvas_view.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'nodes'], 'properties': {'label': {'type': 'string', 'description': 'Label for the merged node. Omit to generate one such as "stg_* (8)".'}, 'nodes': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 40, 'minItems': 2, 'description': 'Node ids or labels to merge. They should be genuinely similar.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'description': {'type': 'string', 'description': 'What the merged node stands for. Defaults to listing what was collapsed.'}}, 'additionalProperties': False}
canvas_connect_nodes
Connect nodes
When: Use to draw the flows that genuinely move data between two nodes. Never connect a zone: connect a node inside it. Draw edges (arrows) between nodes to show how data flows. Label an edge only when the reader could not guess what it does ("CDC", "hourly batch"); obvious flows and dimensional joins read better unlabelled. Edges always render with an arrowhead at the target; bidirectional adds one at the source. Batch: `edges` (up to 60) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_layout_canvas once, when the structure is complete.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'edges'], 'properties': {'edges': {'type': 'array', 'items': {'type': 'object', 'required': ['source', 'target'], 'properties': {'type': {'enum': ['dataflow', 'transformation', 'dependency', 'lineage', 'join'], 'type': 'string', 'description': 'Default "dataflow".'}, 'color': {'type': 'string', 'description': "Override the edge colour (default: the source node's hue)."}, 'label': {'type': 'string', 'description': 'What this connection does, when not obvious.'}, 'style': {'enum': ['solid', 'dashed', 'dotted'], 'type': 'string'}, 'source': {'type': 'string', 'description': 'Upstream node id or label â\x80\x94 data flows FROM here.'}, 'target': {'type': 'string', 'description': 'Downstream node id or label â\x80\x94 data flows TO here.'}, 'bidirectional': {'type': 'boolean', 'description': 'Arrowheads on both ends, for a genuinely two-way link. Not a replacement for existing edges in each direction.'}}, 'additionalProperties': False}, 'maxItems': 60, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_describe_canvas
List every node (flat)
When: Use when you want a flat list of every node, edge and zone. canvas_view shows the same ids as a zone tree with positions and defects, and is usually the better first read. Get an overview of the current canvas: zones as a nested tree in reading order, every node with its id, type, icon and family, all connections with labels, and every note in full. Call this first, before any edit, so you work from real node ids instead of guesses. Operates on one Datadef diagram, named by diagram_id. If you have not already, call get_design_guide first: it carries Datadef's size, edge and zone standard, and diagrams built without it read poorly. Next: canvas_inspect_nodes for a node's full fields, or the write tool you need.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'includeColumns': {'type': 'boolean', 'description': 'Include a short column list for each table node. Default false.'}}, 'additionalProperties': False}
canvas_disconnect_nodes
Remove edges
When: Use to delete specific edges between two nodes. Remove edges, given as source and target, or as an edge id / "Source -> Target" string in `edge`. Batch: `edges` takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'edges'], 'properties': {'edges': {'type': 'array', 'items': {'type': 'object', 'properties': {'edge': {'type': 'string', 'description': 'Edge id, or "Source -> Target".'}, 'source': {'type': 'string', 'description': 'Source node id or label.'}, 'target': {'type': 'string', 'description': 'Target node id or label.'}}, 'additionalProperties': False}, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_group_nodes
Create a zone
When: Use to create a zone (a layer, domain, stage or boundary), nested with `parentGroup`, optionally moving existing nodes into it: the zone is drawn around them where they are, inside the zone they already share. Create a labelled zone (e.g. "Bronze Layer", "Ingestion") and optionally move nodes into it. The zone is drawn around the nodes where they already are, so nothing moves on screen; it nests inside their shared zone unless parentGroup says otherwise. Zones are what turn a tangle of boxes into a readable architecture — use them for layers, domains, or environments. Batch: One zone per call. Create all zones in a single canvas_batch call, outermost first, instead of one call per zone. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. If you have not already, call get_design_guide first: it carries Datadef's size, edge and zone standard, and diagrams built without it read poorly. Next: canvas_add_nodes with `group` set to the zone.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'label'], 'properties': {'color': {'type': 'string', 'description': 'A colour instead of a family, e.g. "green".'}, 'label': {'type': 'string', 'description': 'Zone name, e.g. "Silver Layer".'}, 'nodes': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Node or zone ids or labels to place inside.'}, 'style': {'enum': ['layer', 'cluster', 'swimlane'], 'type': 'string', 'description': 'layer = horizontal band (default), cluster = box, swimlane = vertical lane.'}, 'family': {'enum': ['source', 'ingest', 'bronze', 'silver', 'gold', 'consume', 'dbt', 'neutral'], 'type': 'string', 'description': 'Accent hue encoding the zone role. Zones with different roles get different families.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'description': {'type': 'string'}, 'parentGroup': {'type': 'string', 'description': 'Existing zone to nest this one inside, e.g. "Databricks Workspace". Default: the zone the nodes already share, if any.'}}, 'additionalProperties': False}
canvas_inspect_nodes
Inspect nodes in full
When: Use before changing a node's fields or columns, to see everything it carries: columns, metadata, owners, neighbours. Get full detail for specific nodes: all columns with types and keys, metadata, schedule, formula, owners. Use before modifying a node so you preserve fields you are not changing. Batch: `nodes` (up to 10) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Next: canvas_update_nodes, canvas_set_columns or canvas_replace_node.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'nodes'], 'properties': {'nodes': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 10, 'minItems': 1, 'description': 'Node ids or exact labels. Up to 10 at a time.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_layout_canvas
Lay out the diagram
When: Use once, after the structure (zones, nodes, edges) is complete, not after each change. With no arguments it only places what was added or changed; nothing else moves. Set mode "full", direction (LR/TB/RL), spacing (compact/normal/airy), fit (page-portrait/page-landscape/slide-16:9/square) or zone only when the user asked for a different layout. Position what you added or moved, or re-arrange the diagram. Default (no arguments): places new and moved nodes next to what they connect to, in the reading direction, and grows their zone if needed; nothing else moves. Call it once after structural edits. Re-arranging (mode "full", or any of direction / spacing / fit / zone) redraws the layout the way a generated diagram is drawn, so only do it when the user asks for a different layout: "make it vertical" → direction TB; "more breathing room" / "less cramped" → spacing airy; "fit a Word doc / paper / A4" → fit page-portrait; "for a slide" → fit slide-16:9; "tidy this zone" → zone. Notes and flow arrows follow what they annotate. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result, then notes and flow arrows, then canvas_validate_canvas.
Destructive Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'fit': {'enum': ['none', 'page-portrait', 'page-landscape', 'slide-16:9', 'square'], 'type': 'string', 'description': 'Shape the diagram for a format: page-portrait = A4 / Word / paper; slide-16:9 = presentation.'}, 'full': {'type': 'boolean', 'description': 'Same as mode "full". Prefer `mode`.'}, 'mode': {'enum': ['place', 'full'], 'type': 'string', 'description': '"place" (default) positions only new or moved nodes and moves nothing else. "full" re-arranges everything (or just `zone`) â\x80\x94 only when the user asked for a different layout.'}, 'zone': {'type': 'string', 'description': 'Re-arrange only this zone (id or label); it keeps its place and neighbours make room.'}, 'spacing': {'enum': ['compact', 'normal', 'airy'], 'type': 'string', 'description': 'Gaps between things for a re-arrange. "airy" when the user wants more whitespace, "compact" to save space.'}, 'direction': {'enum': ['LR', 'TB', 'RL'], 'type': 'string', 'description': 'Reading direction for a re-arrange: LR left-to-right, TB top-to-bottom, RL right-to-left. Default: the direction the diagram reads in now.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_measure_canvas
Measure exact geometry
When: Use only for a precise manual placement the user asked for: exact x/y/width/height per node. To check a layout, canvas_view is faster and already reports overlaps. Get exact geometry: every node's position and size in canvas units, the overall canvas bounds, and any nodes that overlap each other. Call this before moving, resizing, or placing anything precisely — positions are meaningless without it. Batch: `nodes` takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Next: canvas_move_nodes, canvas_resize_nodes or canvas_align_nodes.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'nodes': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Limit to specific node ids or labels. Omit to measure everything.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_move_nodes
Move nodes by hand
When: Use only when the user asked for a specific placement. Moving a zone moves its children; never move the children as well. Set node positions precisely. Use absolute x/y to place something exactly, or dx/dy to nudge it. Coordinates are absolute canvas units (same space canvas_measure_canvas reports). Moving a group moves its children with it — do not also move those children in the same call. Call canvas_measure_canvas first. Batch: `moves` (up to 60) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check. Do not run canvas_layout_canvas afterwards: it would undo the placement.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'moves'], 'properties': {'moves': {'type': 'array', 'items': {'type': 'object', 'required': ['node'], 'properties': {'x': {'type': 'number', 'description': 'Absolute x. Omit to keep current x.'}, 'y': {'type': 'number', 'description': 'Absolute y. Omit to keep current y.'}, 'dx': {'type': 'number', 'description': 'Relative horizontal shift. Ignored if x is given.'}, 'dy': {'type': 'number', 'description': 'Relative vertical shift. Ignored if y is given.'}, 'node': {'type': 'string', 'description': 'Node id or exact label.'}}, 'additionalProperties': False}, 'maxItems': 60, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_move_to_group
Move nodes into a zone
When: Use to move existing nodes or zones into another zone (they are placed inside it and the zone grows to fit), or out of every zone with group null. A zone cannot move into its own sub-zone. Move existing nodes or zones into an existing zone, or out of every zone (group: null). They keep their place on screen when they already sit inside the zone; otherwise they are placed inside it and the zone grows to fit. A zone cannot move into its own sub-zone. Batch: `nodes` takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'nodes', 'group'], 'properties': {'group': {'type': ['string', 'null'], 'description': 'Target zone id or label. Pass null to take the nodes out of their zones.'}, 'nodes': {'type': 'array', 'items': {'type': 'string'}, 'minItems': 1, 'description': 'Node or zone ids or labels to move.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_remove_lineage
Remove column lineage
When: Use to delete lineage rows between two nodes (one column pair, or all rows between them). Lineage pointing at deleted nodes or columns is cleaned automatically. Delete lineage rows between two nodes: one column pair, or every row between the two nodes when no column is given. Lineage pointing at deleted nodes or columns is cleaned automatically and never needs this. Batch: `links` (up to 100) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'links'], 'properties': {'links': {'type': 'array', 'items': {'type': 'object', 'required': ['sourceNode', 'targetNode'], 'properties': {'sourceNode': {'type': 'string', 'description': 'Upstream node id or label.'}, 'targetNode': {'type': 'string', 'description': 'Downstream node id or label.'}, 'sourceColumn': {'type': 'string', 'description': 'Only rows from this column.'}, 'targetColumn': {'type': 'string', 'description': 'Only rows to this column.'}}, 'additionalProperties': False}, 'maxItems': 100, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_remove_nodes
Remove nodes
When: Use to delete nodes and their edges. Removing a zone keeps its contents (they move up to the parent, same place on screen): that is how to ungroup. Pass keepChildren:false only to delete the zone with everything inside it. Delete nodes, notes or zones, with every edge and lineage row touching them. Removing a zone keeps its contents by default: they move up to the zone's parent and stay where they are on screen (this is how to ungroup a zone). Pass keepChildren:false only when the user wants the zone AND everything inside it deleted. Batch: `nodes` takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'nodes'], 'properties': {'nodes': {'type': 'array', 'items': {'type': 'string'}, 'minItems': 1, 'description': 'Node or zone ids or exact labels.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'keepChildren': {'type': 'boolean', 'description': 'For zones: true (default) moves the contents up to the parent; false deletes everything inside too.'}}, 'additionalProperties': False}
canvas_replace_node
Replace a node in place
When: Use when one component changes identity or type (Redshift becomes Snowflake, a card becomes a service icon). The node keeps its id, connections, lineage, zone, position and fields. Turn a node into a different component in place — Redshift becomes Snowflake, a batch job becomes streaming. It keeps its id, every connection and lineage row, its zone, position, owners, schedule, colours and columns; only what you pass changes (a new label with no icon picks the new product's icon). canvas_update_nodes does the same for many nodes at once. Batch: One node per call. To convert many nodes, use canvas_update_nodes with `type` (and `label`, `icon`) for each, in one call. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'node', 'label'], 'properties': {'icon': {'type': 'string', 'description': 'Icon id from search_icons.'}, 'node': {'type': 'string', 'description': 'Node id or exact label to replace.'}, 'type': {'enum': ['table', 'kpi', 'dataSource', 'pipeline', 'consumption', 'serviceIcon'], 'type': 'string', 'description': 'New type. Omit to keep the current type.'}, 'label': {'type': 'string', 'description': 'New label.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'technology': {'type': 'string'}, 'description': {'type': 'string'}, 'keepColumns': {'type': 'boolean', 'description': 'Keep the existing columns (table to table). Default true; false clears them.'}}, 'additionalProperties': False}
canvas_resize_nodes
Resize nodes by hand
When: Use only when the user asked for a specific size. Set the width and height of nodes. Mostly for shapes, text boxes, and group zones — data nodes size themselves from their content, and resizing one can clip what it displays. Batch: `resizes` (up to 40) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check.
Destructive
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'resizes'], 'properties': {'resizes': {'type': 'array', 'items': {'type': 'object', 'required': ['node'], 'properties': {'node': {'type': 'string', 'description': 'Node id or exact label.'}, 'width': {'type': 'number', 'maximum': 4000, 'minimum': 20}, 'height': {'type': 'number', 'maximum': 4000, 'minimum': 20}}, 'additionalProperties': False}, 'maxItems': 40, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_search_icons
Find vendor icon ids
When: Use before adding nodes that should show a vendor logo (Snowflake, Kafka, Power BI) and you are unsure of the icon id. Find icon ids in Datadef's library (2000+ cloud and data-tool logos) by product name, e.g. "Amazon Aurora PostgreSQL", "k8s", "Azure Event Hubs". Pass `queries` to look up many names in one call (best id per name); pass `query` for the top matches of one name. Scores: 90+ sure, 75+ good. A name with no match has no icon; leave the icon field out rather than guessing. Batch: Pass `queries` with every vendor at once (up to 40, best id per name) instead of one call per vendor. Next: canvas_add_nodes (or canvas_update_nodes) with icon set to a returned id; omit icon when nothing matched.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 10, 'minimum': 1, 'description': 'Matches per name. Default 5 for `query`, 1 for `queries`.'}, 'query': {'type': 'string', 'minLength': 1, 'description': 'One product or tool name.'}, 'queries': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'maxItems': 40, 'description': 'Several names at once, e.g. ["Snowflake", "Fivetran", "Power BI"]. Returns the best icon for each.'}, 'diagram_id': {'type': 'string', 'description': 'Not needed for icon search; accepted for compatibility.'}}, 'additionalProperties': False}
canvas_set_columns
Change a table's columns
When: Use `mode: "merge"` to add or update (renameTo) a few columns, `mode: "remove"` to drop some, or the default replace for the full list. Columns that stay keep their ids and lineage. Change a table's columns. mode "merge" adds new columns and updates (or renames, with renameTo) the ones you name, leaving the rest alone — use it to add one column. mode "remove" deletes the named columns only. mode "replace" (default) makes the list exactly what you pass. Columns are matched by name, so a column that stays keeps its id, its lineage and the edges anchored to it; lineage and anchors of removed columns are cleaned up. Mark primary and foreign keys. Batch: One table per call. For several tables, send one set_columns operation per table in a single canvas_batch call. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_add_lineage for column-level mappings, if there are any.
Destructive Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'node', 'columns'], 'properties': {'mode': {'enum': ['replace', 'merge', 'remove'], 'type': 'string', 'description': 'Default "replace".'}, 'node': {'type': 'string', 'description': 'Table node id or exact label.'}, 'columns': {'type': 'array', 'items': {'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Column name, e.g. "customer_id".'}, 'type': {'type': 'string', 'description': 'SQL type, e.g. "varchar", "bigint", "timestamp". Default "unknown" for a new column; an existing column keeps its type.'}, 'renameTo': {'type': 'string', 'description': 'merge mode: new name for the column called `name`.'}, 'description': {'type': 'string', 'description': 'What the column means in business terms.'}, 'isForeignKey': {'type': 'boolean'}, 'isPrimaryKey': {'type': 'boolean'}}, 'additionalProperties': False}, 'maxItems': 80}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_suggest_simplifications
Suggest simplifications
When: Use when the diagram feels dense or the user asks to simplify. It changes nothing; it reports what could collapse. Report where this canvas could be collapsed — groups of similar nodes that could become one summary node — without changing anything. Use it to decide whether the diagram is denser than it needs to be. Density is not automatically a problem: keep the detail when the detail is the point. Operates on one Datadef diagram, named by diagram_id. Next: canvas_collapse_nodes to apply a suggestion the user wants.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'minGroupSize': {'type': 'integer', 'maximum': 20, 'minimum': 2, 'description': 'Smallest group worth reporting. Default 3.'}}, 'additionalProperties': False}
canvas_update_edges
Update edges
When: Use to relabel, retype, restyle (dashed, colour), reverse, put arrowheads on both ends, or re-point an existing edge, instead of disconnecting and reconnecting it. Change existing connections in place: relabel, retype, restyle (solid/dashed/dotted, colour), reverse the direction, put arrowheads on both ends, or re-point one end to another node. Identify each edge by source and target, or by `edge` (an id or "Source -> Target"). Change only the edges the user asked about: a request and its response are two edges on purpose, never merge them into one two-headed edge to tidy the drawing. Batch: `updates` (up to 60) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'updates'], 'properties': {'updates': {'type': 'array', 'items': {'type': 'object', 'properties': {'edge': {'type': 'string', 'description': 'Edge id, or "Source -> Target".'}, 'type': {'enum': ['dataflow', 'transformation', 'dependency', 'lineage', 'join'], 'type': 'string'}, 'color': {'type': 'string', 'description': 'Colour name or hex; "default" returns to the source node\'s hue.'}, 'label': {'type': 'string', 'description': 'New label.'}, 'style': {'enum': ['solid', 'dashed', 'dotted'], 'type': 'string'}, 'source': {'type': 'string', 'description': 'Current source node id or label.'}, 'target': {'type': 'string', 'description': 'Current target node id or label.'}, 'reverse': {'type': 'boolean', 'description': 'Swap source and target: the arrow points the other way.'}, 'newSource': {'type': 'string', 'description': 'Re-point the edge to start at this node.'}, 'newTarget': {'type': 'string', 'description': 'Re-point the edge to end at this node.'}, 'removeLabel': {'type': 'boolean', 'description': 'Remove the label.'}, 'bidirectional': {'type': 'boolean', 'description': 'true = arrowheads on both ends of this one edge (a genuinely two-way link); false = only at the target.'}}, 'additionalProperties': False}, 'maxItems': 60, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_update_nodes
Update nodes, zones and notes
When: Use for any in-place change: rename a node or zone (it keeps its size and contents), edit a note's text, recolour (`color: "green"`, `fill`, `family`), change a zone's style, swap an icon, or change a data node's type; fields you do not pass stay as they are. Many nodes in one call. Change existing nodes, zones or notes in place: rename (a zone keeps its size and contents), edit a note's text, recolour ("color": "green" or "#16a34a"; "fill" for the background; "family" for a layer hue), change a zone's style, swap an icon, change a data node's type. Only the fields you pass change; id, position, size, edges and everything else are kept. Batch many nodes in one call. For columns use canvas_set_columns. Batch: `updates` (up to 60) takes a list; put every item in one call rather than one call per item. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
Destructive Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'updates'], 'properties': {'updates': {'type': 'array', 'items': {'type': 'object', 'required': ['node'], 'properties': {'fill': {'$ref': '#/properties/updates/items/properties/color', 'description': 'Background / wash colour. Name or hex.'}, 'icon': {'type': 'string', 'description': 'Icon id from search_icons, or "none" to remove it. An unknown icon is not applied.'}, 'node': {'type': 'string', 'description': 'Node or zone id, or exact label.'}, 'text': {'type': 'string', 'description': 'New text of a note / text box (same as label for notes).'}, 'type': {'enum': ['table', 'kpi', 'dataSource', 'pipeline', 'consumption', 'serviceIcon'], 'type': 'string', 'description': "Change a data node's type in place (same id, edges, zone and position). serviceIcon needs an icon."}, 'color': {'type': 'string', 'description': "Main colour: a zone's border and header, a card's tile and border, a note's border, a shape's stroke. Name, hex, or family."}, 'label': {'type': 'string', 'description': 'New name. For a zone this renames its caption; for a note it replaces the note text.'}, 'family': {'enum': ['source', 'ingest', 'bronze', 'silver', 'gold', 'consume', 'dbt', 'neutral'], 'type': 'string', 'description': 'Colour family for a node or zone. Clears custom colours.'}, 'kpiUnit': {'type': 'string'}, 'schedule': {'type': 'string'}, 'container': {'enum': ['layer', 'boundary'], 'type': 'string', 'description': 'Zones only: layer = tinted band with a header; boundary = dashed perimeter (account, VPC, workspace).'}, 'dataOwner': {'type': 'string'}, 'kpiTarget': {'type': 'string'}, 'textColor': {'$ref': '#/properties/updates/items/properties/color', 'description': 'Text colour. Name or hex.'}, 'zoneStyle': {'enum': ['layer', 'cluster', 'swimlane'], 'type': 'string', 'description': 'Zones only: layer = horizontal band, cluster = box, swimlane = vertical lane.'}, 'kpiFormula': {'type': 'string'}, 'resetStyle': {'type': 'boolean', 'description': 'Drop custom colours and family, back to the default look. Applied before any colour in the same update.'}, 'technology': {'type': 'string'}, 'borderStyle': {'enum': ['solid', 'dashed', 'dotted'], 'type': 'string', 'description': 'Border line of a zone or card; line style of an arrow or line shape.'}, 'dataSteward': {'type': 'string'}, 'description': {'type': 'string'}, 'pipelineType': {'type': 'string'}, 'teamInCharge': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}, 'maxItems': 60, 'minItems': 1}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_validate_canvas
Validate the diagram
When: Use before you finish: broken references and icons, nodes outside their zone, overlapping zones or nodes. Loops are reported as information only. Check your work: broken references, broken icons, nodes sticking out of their zone, overlapping zones or nodes, unconnected or unfed nodes. By default it reports only issues in what you changed in this session (scope "changed"); scope "all" checks the whole canvas. Fix errors; judge warnings; info needs no action. Operates on one Datadef diagram, named by diagram_id. Next: Fix errors. Warnings are observations; ignore the ones that do not apply.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'scope': {'enum': ['changed', 'all'], 'type': 'string', 'description': '"changed" (default when you have changed something) or "all".'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}}, 'additionalProperties': False}
canvas_view
View the diagram (fast)
When: use to see a diagram before you edit it and after each round of changes; this is how you check your work. It answers in milliseconds from the saved diagram, where export_diagram starts a browser for 6-10 s. Returns a text map: the zones as a tree, each with its place on a coarse grid (r1 = top row, c1 = left column) and its nodes (label, type, icon, #id), then the edges, then the checks a render would reveal: overlapping nodes, overlapping sibling zones, nodes sticking out of their zone, nodes not laid out yet, empty zones, and the validator's error and warning counts. Every #id works as a node reference in the canvas_* tools. It also says when an edit_diagram run or a generation is still in progress on the diagram, and gives a preview image link that renders only if opened. For a large diagram, pass zone to look at one zone. include_image also renders a PNG (slow: only when you need to see styling). Next: fix what the checks report with the targeted canvas_* tool, then canvas_view again.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'zone': {'type': 'string', 'description': 'Zone id or exact label: show only that zone and what it contains.'}, 'diagram_id': {'type': 'string', 'description': 'Diagram id, from list_diagrams, create_diagram or create_blank_diagram.'}, 'include_edges': {'type': 'boolean', 'description': 'List the edges. Default true.'}, 'include_image': {'type': 'boolean', 'description': 'Also render a PNG, 6-10 s. Default false.'}, 'include_columns': {'type': 'boolean', 'description': 'List column names under each table. Default false.'}}, 'additionalProperties': False}
create_blank_diagram
Create an empty diagram to build yourself
When: use when you will build the diagram yourself with the canvas_* tools, because you want control over the result or already know the architecture from the conversation. Use create_diagram instead when Datadef's model should design the whole thing from a prompt. Creates an empty diagram and returns its diagram_id. No AI generation runs: you draw it. Call get_design_guide first: it is the standard Datadef's own generator follows, and building without it produces the diagrams this tool exists to avoid. Next: canvas_search_icons (all vendors in one call), then one canvas_batch with every zone (group_nodes) and node (add_nodes), canvas_connect_nodes, canvas_layout_canvas once, canvas_view.
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'name': {'type': 'string', 'description': 'Diagram name. Defaults to "Untitled diagram".'}, 'description': {'type': 'string', 'description': 'Optional short description.'}}, 'additionalProperties': False}
create_diagram
Create a data architecture diagram
When: use when Datadef's own model should design a whole new diagram from a description or a pasted schema. To build it yourself step by step, use create_blank_diagram; to change an existing diagram, canvas_view and the canvas_* tools, or edit_diagram. Generates a professional data architecture diagram from a description and saves it to the user's Datadef account. Use it for any data-shaped diagram: medallion and lakehouse architectures, ETL/ELT pipelines, streaming topologies, data mesh, star and snowflake schemas, ER diagrams, lineage maps, cloud architectures, and data platform designs. EXISTING SCHEMAS: if the conversation or the repository has the schema itself (SQL DDL, a MySQL or pg_dump export, migrations, schema.prisma), pass the file contents as the prompt, unedited. Datadef parses it instead of asking a model: every table, column, type, primary key and foreign key comes out exactly as written, in seconds. Warehouse DDL with no declared foreign keys (fact_sales.customer_key → dim_customer.customer_key) gets its links from key names, drawn dashed. Add a sentence only if you want something other than a picture of that schema; "turn these tables into a star schema" or "design the pipeline that loads them" goes to the model instead. Write a specific prompt. Name the actual technologies (Snowflake, dbt, Airflow, Kafka, Fivetran), the layers or zones you want, and the tables that matter, the diagram is only as detailed as the description. Zone names you give are treated as a specification, not a suggestion. SCOPE: if the user's request is open-ended ("diagram our platform", "show me something"), ask them how much detail they want before calling this, or say which scope you chose. Default to scope "overview". A dense 40-node diagram is impressive and usually not what someone wanted from a one-line request; they can always ask you to expand it. TIMING: this waits up to ~35 seconds; fast generations come back finished, with a preview image and a markdown line to show the user. Slower ones (1-3 minutes total) return a diagram_id while generation continues: call get_diagram with that id after ~60 seconds (poll every 30s) to get the finished diagram. If you cannot call tools again on your own, never leave the user empty-handed: give them the Open link, say it will be ready in about a minute, and offer to show the diagram inline when they next ask. Never call create_diagram a second time while one is still generating; you would create a duplicate. Do not use image generation for these. This produces a real, editable diagram. Next: show the user the preview line it returns; to adjust the result, canvas_view then the targeted canvas_* tools.
Open world
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['prompt'], 'properties': {'name': {'type': 'string', 'description': 'Title for the diagram. Defaults to an AI-chosen title.'}, 'scope': {'enum': ['overview', 'detailed'], 'type': 'string', 'description': 'overview (default): ~12-20 nodes, the shape of the system, right for almost every open-ended request. detailed: every object itemised, denser and harder to read. Ask the user rather than assuming they want detailed.'}, 'prompt': {'type': 'string', 'minLength': 10, 'description': 'What to diagram. Include technologies, data sources, transformations, layers, and destinations.'}, 'detailed': {'type': 'boolean', 'description': 'Use a higher-tier model. Slower and roughly 10x the cost, only when the user explicitly asks for maximum quality. Independent of `scope`.'}}, 'additionalProperties': False}
edit_diagram
Edit a diagram with Datadef's agent
When: use for a large change you can describe in words better than you can make it tool by tool: "reorganise this into bronze, silver and gold", "rebuild the consumption side from this spec", "add owners and schedules everywhere". For a precise change (rename, add a node, rewire an edge), the canvas_* tools are faster and exact. Datadef's own editing agent carries out the instruction: add nodes, rewire connections, add columns, reorganise into layers, fill in owners and schedules. Be specific about what to change and where: "Add a Kafka topic between the API and the bronze table, labelled 'events'" works; "make it better" does not. Timing: an edit takes 30-120 s. This waits about 35 s; a finished edit comes back with its summary, the ids it changed and a PNG. A slower one answers "in progress" and keeps running on the server: do NOT call edit_diagram again. Sending the same instruction again joins the running edit (or returns the result of the one that finished less than a minute ago); a different instruction is refused until it finishes. canvas_view and get_diagram report when it has finished. Next: canvas_view to check the result.
Destructive Open world
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id', 'instruction'], 'properties': {'diagram_id': {'type': 'string', 'description': 'Diagram id to modify.'}, 'instruction': {'type': 'string', 'minLength': 3, 'description': 'What to change, in plain language.'}, 'include_image': {'type': 'boolean', 'description': 'Return a PNG of the updated diagram when the edit finishes in time. Default true.'}}, 'additionalProperties': False}
export_diagram
Export a diagram as an image
When: use to give the user an image of a diagram, or a link to download, attach or embed one. Not to check your own edits: a render starts a browser (6-10 s), while canvas_view answers in milliseconds and reports overlaps. Renders a diagram to PNG or JPEG. Returns the image inline AND a short-lived signed download URL. Use the inline image to show the diagram; use the URL when the user wants to save it, attach it, or share a link: it serves the file directly and needs no API key. Next: nothing; show the image or the link to the user.
Read only
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'width': {'type': 'integer', 'maximum': 4000, 'minimum': 600, 'description': 'Viewport width in pixels. Default 1600.'}, 'format': {'enum': ['png', 'jpeg'], 'type': 'string', 'description': 'Default png.'}, 'height': {'type': 'integer', 'maximum': 4000, 'minimum': 400, 'description': 'Viewport height in pixels. Default 1000.'}, 'diagram_id': {'type': 'string', 'description': 'Canvas id to export.'}}, 'additionalProperties': False}
get_design_guide
Datadef design guide
When: read once before your first canvas_* call, to build or to edit. Datadef's standard for a readable diagram (size, edge discipline, nested zones, notes) and the tool workflow: which canvas_* tool to use when, batching, laying out once, checking with canvas_view. It is the same standard Datadef's own generator follows, so a diagram you build by hand comes out indistinguishable from a generated one. Works without a subscription. Next: create_blank_diagram to build, or canvas_view to edit an existing diagram.
Read only Idempotent
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}
get_diagram
Read a diagram, with a picture
When: use to show the user a diagram (it attaches a rendered PNG and a markdown image line, 6-10 s), or to poll a diagram that create_diagram or edit_diagram is still working on. To check your own edits, canvas_view is faster and reports overlaps. Returns every node with its type and columns, every connection and the zones, plus whether a generation or edit_diagram run is still in progress. Next: canvas_view and the canvas_* tools to edit.
Read only
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['diagram_id'], 'properties': {'diagram_id': {'type': 'string', 'description': 'Canvas id, from list_diagrams, create_diagram, or create_blank_diagram.'}, 'include_image': {'type': 'boolean', 'description': 'Attach a PNG preview and a markdown image link to show the user. Default true; pass false for structure-only reads.'}, 'include_columns': {'type': 'boolean', 'description': 'Include table column lists. Default true.'}}, 'additionalProperties': False}
list_diagrams
List the user's diagrams
When: use to find the id of an existing diagram before viewing, editing or exporting it. Lists the diagrams in the user's Datadef account, most recently updated first. Next: canvas_view with the diagram_id to see it.
Read only
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Max results. Default 25.'}}, 'additionalProperties': False}
repo_refresh
Sync a diagram from its repository
Re-sync a repo-linked diagram from the current state of its repository. If the tracked branch or tag has not moved since the last sync, nothing changes. If it has, the diagram is REGENERATED from the repository, which replaces manual canvas edits. Only the owner of the repository connection can use this.
Destructive Open world
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['project_id'], 'properties': {'project_id': {'type': 'string', 'description': 'Project id of the repo-linked diagram. A diagram_id from list_diagrams works too.'}}, 'additionalProperties': False}
repo_status
Repository sync status
For a diagram that was created from a connected git repository: which repo and branch or tag it tracks, when it last synced, the commit it reflects, and whether daily sync is on. Use repo_refresh to sync it now. Only the owner of the repository connection can use this.
Read only
Input schema 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['project_id'], 'properties': {'project_id': {'type': 'string', 'description': 'Project id of the repo-linked diagram. A diagram_id from list_diagrams works too.'}}, 'additionalProperties': False}
History

Recent tool changes

Changed
export_diagram
Oct. 1, 2026, 2:44 a.m.
Changed
edit_diagram
Oct. 1, 2026, 2:44 a.m.
Changed
get_diagram
Oct. 1, 2026, 2:44 a.m.
Changed
list_diagrams
Oct. 1, 2026, 2:44 a.m.
Changed
create_blank_diagram
Oct. 1, 2026, 2:44 a.m.
Changed
create_diagram
Oct. 1, 2026, 2:44 a.m.
Added
canvas_batch
Oct. 1, 2026, 2:44 a.m.
Added
canvas_view
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_validate_canvas
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_layout_canvas
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_align_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_resize_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_move_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_collapse_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_suggest_simplifications
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_add_region
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_add_flow_arrow
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_add_shape
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_add_text
Oct. 1, 2026, 2:44 a.m.
Added
canvas_remove_lineage
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_add_lineage
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_move_to_group
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_group_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_set_columns
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_disconnect_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_update_edges
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_connect_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_remove_nodes
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_replace_node
Oct. 1, 2026, 2:44 a.m.
Changed
canvas_update_nodes
Oct. 1, 2026, 2:44 a.m.
Discover

Similar MCP servers

Blixtworks

com.blixtworks.www/tools

Offers pay-per-call utilities for text, image processing and analysis, data conversion, validation, web inspection, cryptography,…

chartlink

io.github.oscarleoo/chartlink

Creates, styles, publishes, embeds, and automatically refreshes charts and tables from inline data or scheduled external data sou…

GripForge

io.github.gripforgeai/mcp

Generates, rigs, animates, analyzes, and packages game characters, weapons, armor, effects, environments, and engine-ready assets.

spriteship

com.spriteship/spriteship

Generates and manages 2D game characters, assets, animations, tilesets, UI packs, maps, and engine-ready exports for multiple gam…

Thousand API

com.thousand-api/thousand-api

Provides deterministic data conversion, validation, JSON transformation, statistical calculations, date and schedule utilities, i…

HubVibe: Pay-per-Call Tools for AI Agents: Web Search, Email Verify, KYC, Stocks, Crypto, News, Data

io.github.Its-fortunatefolly/hubvibe

Offers paid utilities for web audits, HTTP fetching and extraction, BigQuery analysis, LLM processing, code execution, blockchain…

Compose Preview Catalogs

io.github.yschimke/compose-preview

Browses, renders, compares, audits, and edits Jetpack Compose preview catalogs and associated UI designs.

arch-tools-mcp

io.github.Deesmo/arch-tools-mcp

Provides general-purpose agent APIs for browser automation, web and PDF extraction, data conversion, email operations, fact check…