MCP Radar
MCP-Server

Georgia Civic Data

org.georgiacivicdata/georgia-civic-data
Daten & Analytik Bildung Öffentlich und erreichbar MCP 2025-11-25

Was dieses MCP kann

Queries, aggregates, joins, and resolves entities across Georgia education, Census, and immigration datasets.

Funktionen

Tools

12 Tools
aggregate
Compute a grouped aggregate over one topic — the aggregation-first path. `agg` is one of avg/sum/min/max/count/weighted_rate; `metric` is a metric column (DEFAULTS to the topic key_metric; ignored for count); `group_by` is a list of grain columns (year, FK codes like district_code or county_fips, or categoricals — see describe_dataset). `weighted_rate` computes a true population-weighted SUM(numerator)/SUM(denominator) for a rate key metric (when the contract declares the components) — prefer it over `avg` for a rate across multiple places/years, since `avg` means the per-row rates and ignores population. Supports the same `filters` / `year` / `year_min`-`year_max` / `detail` as query_dataset, plus `order_by`+`order` for top-N (order_by 'value' for the aggregated column; NULL cells sort LAST in either direction). Returns one small row per group with `<metric>_<agg>` (or `row_count`) plus coverage diagnostics (input_rows / non-null counts) so suppression is visible; `aggregation_scope` flags whether rows are source-published at this grain or recomputed from a finer detail (prefer source-published — see the advisory). A `sum`/`weighted_rate` ACROSS a column the contract declares non_additive (overlapping rows, e.g. county rows that count one application in several counties) still returns, but carries a top-level `non_additive` block and a leading `non_additive_sum` advisory: that figure is NOT a total — group_by the column or use the published total row instead. Aggregates SKIP NULLs and NULL means SUPPRESSED not zero. No raw SQL: all identifiers are contract-allowlisted.
Eingabeschema 
{'type': 'object', 'title': 'aggregateArguments', 'required': ['topic'], 'properties': {'agg': {'type': 'string', 'title': 'Agg', 'default': 'avg'}, 'year': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Year', 'default': None}, 'limit': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Limit', 'default': None}, 'order': {'type': 'string', 'title': 'Order', 'default': 'asc'}, 'topic': {'type': 'string', 'title': 'Topic'}, 'detail': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Detail', 'default': None}, 'metric': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Metric', 'default': None}, 'offset': {'type': 'integer', 'title': 'Offset', 'default': 0}, 'filters': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Filters', 'default': None}, 'group_by': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Group By', 'default': None}, 'order_by': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Order By', 'default': None}, 'year_max': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Year Max', 'default': None}, 'year_min': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Year Min', 'default': None}, 'main_topic': {'type': 'string', 'title': 'Main Topic', 'default': 'education'}}}
Ausgabeschema 
{'type': 'object', 'title': 'aggregateDictOutput', 'additionalProperties': True}
describe_dataset
Full schema for one topic: every column (name/type/role/unit/value range/null-meaning), the exact `filters` list with enum values (read this before query_dataset — it is the authoritative set of filter keys), the FK→dimension join shape (`foreign_keys`), example queries, usage, limitations, null semantics, tags, and `schema_hash` (for cache/drift detection). The top-level `key_metric` names the single headline column most answers want; each column carries `key_metric_grain_contributor` (a grain axis the key metric is only comparable within — pin or group by it) and `metric_component` (numerator/denominator of a rate/average metric). `recommended_query` gives the safe default query shape (key metric + filters to pin + required single-selects) plus a `ranking` recipe for top/bottom-N asks; `filter_hints` lists paired filters; `non_additive` lists columns whose rows overlap (never sum across them; a metric entry names metric columns never to add together) and `value_implications` values that imply another column's value; each categorical filter carries `has_total` / `requires_single_value`. Pass `verbosity='schema'` for a much smaller payload that drops the prose (description/usage/limitations/example queries/column descriptions) but keeps every field needed to compose a correct query — use it when you only need the filter keys and enums; prefer the default 'full' before reporting conclusions (the limitations prose carries the caveats). On an unknown topic returns a self-describing error listing available topics + a 'did you mean' hint. `main_topic` defaults to 'education'; pass 'census' for Census topics or 'immigration' for immigration topics.
Eingabeschema 
{'type': 'object', 'title': 'describe_datasetArguments', 'required': ['topic'], 'properties': {'topic': {'type': 'string', 'title': 'Topic'}, 'verbosity': {'type': 'string', 'title': 'Verbosity', 'default': 'full', 'description': "'full' (default) or 'schema' (drops prose; keeps columns/filters/enums/key_metric/recommended_query)."}, 'main_topic': {'type': 'string', 'title': 'Main Topic', 'default': 'education'}}}
Ausgabeschema 
{'type': 'object', 'title': 'describe_datasetDictOutput', 'additionalProperties': True}
describe_dimension
Schema for one dimension (districts / schools / counties / demographics): the (possibly composite) primary key, the attribute columns a join attaches, the cross-dataset `link_keys` (e.g. districts.district_census_id → Census via the crosswalk — a 5-digit school-district code, NOT a county FIPS), and demographics `semantics` (within a category the values are mutually exclusive; `all` is the denominator). Read this before writing a link_query join.
Eingabeschema 
{'type': 'object', 'title': 'describe_dimensionArguments', 'required': ['name'], 'properties': {'name': {'type': 'string', 'title': 'Name'}}}
Ausgabeschema 
{'type': 'object', 'title': 'describe_dimensionDictOutput', 'additionalProperties': True}
distinct_values
List the distinct values of ONE filterable column of a topic — the fast way to learn valid filter values before query_dataset, especially for FREE categoricals and FK codes (district_code/school_code/county_fips/demographic) that carry no enum in describe_dataset (a wrong guess otherwise returns an empty page with no error). `column` must be a filterable column (see describe_dataset's `filters`). Optional `prefix` does a case-insensitive starts-with filter; `limit` caps results (default 50). Enum-bearing columns return their contract enum directly; others run a capped SELECT DISTINCT over the gold data. `truncated` flags when the list is capped.
Eingabeschema 
{'type': 'object', 'title': 'distinct_valuesArguments', 'required': ['topic', 'column'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 50}, 'topic': {'type': 'string', 'title': 'Topic'}, 'column': {'type': 'string', 'title': 'Column'}, 'detail': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Detail', 'default': None}, 'prefix': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Prefix', 'default': None}, 'main_topic': {'type': 'string', 'title': 'Main Topic', 'default': 'education'}}}
Ausgabeschema 
{'type': 'object', 'title': 'distinct_valuesDictOutput', 'additionalProperties': True}
get_contract
Return the authoritative ODCS v3.2 data contract for a topic (kind='topic') or a dimension (kind='dimension') so you can consume the machine-readable schema without cloning the repo. fmt='yaml' (default) returns the document verbatim as text; fmt='json' returns it parsed. Only approved topics and loaded dimensions expose a contract.
Eingabeschema 
{'type': 'object', 'title': 'get_contractArguments', 'required': ['name'], 'properties': {'fmt': {'type': 'string', 'title': 'Fmt', 'default': 'yaml'}, 'kind': {'type': 'string', 'title': 'Kind', 'default': 'topic'}, 'name': {'type': 'string', 'title': 'Name'}, 'main_topic': {'type': 'string', 'title': 'Main Topic', 'default': 'education'}}}
Ausgabeschema 
{'type': 'object', 'title': 'get_contractDictOutput', 'additionalProperties': True}
get_dimension
Paginated read of a dimension table — the label lookups (district names, school names, county names, demographic labels). Rows are ordered by the dimension's primary key so paging is stable. Use describe_dimension for the schema and link keys. Small page defaults; `truncated` + a `bulk_export` pointer signal when to pull the full table elsewhere.
Eingabeschema 
{'type': 'object', 'title': 'get_dimensionArguments', 'required': ['name'], 'properties': {'name': {'type': 'string', 'title': 'Name'}, 'limit': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Limit', 'default': None}, 'offset': {'type': 'integer', 'title': 'Offset', 'default': 0}}}
Ausgabeschema 
{'type': 'object', 'title': 'get_dimensionDictOutput', 'additionalProperties': True}
link_query
Run a cross-dataset / cross-topic analytical SQL query that the per-topic query_dataset filters can't express — e.g. join education, Census, or immigration facts to a dimension (or another dataset) on shared geography (immigration and Census county topics share county_fips directly). READ-ONLY, SANDBOXED DuckDB: one SELECT (or WITH … SELECT); no DDL/DML/COPY/ATTACH/INSTALL/PRAGMA/SET/CALL; you may only read_parquet() the curated gold paths returned by link_tables (call it first and paste the snippets) — querying a file path directly is rejected. Joins use the keys from describe_dimension's link_keys (districts.district_census_id bridges to Census via the crosswalk — it is a school-district code, not a county FIPS, so a district is not 1:1 with a county). Results are row- and byte-capped and time-limited; `truncated` flags when capped — add aggregation or a tighter WHERE rather than dumping rows. NULL means suppressed, not zero. On a violation you get a self-describing error naming the offending token/path.
Eingabeschema 
{'type': 'object', 'title': 'link_queryArguments', 'required': ['sql'], 'properties': {'sql': {'type': 'string', 'title': 'Sql'}, 'limit': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Limit', 'default': None}}}
Ausgabeschema 
{'type': 'object', 'title': 'link_queryDictOutput', 'additionalProperties': True}
link_tables
List the tables link_query can read (curated gold paths only) and the join keys that bridge facts → dimensions → Census geography. Call this BEFORE writing a link_query. Two-tier to stay context-cheap: with NO arguments it returns a LEAN index — every table's name, grain, detail levels, default `read_parquet(...)` snippet, and join keys (enough to pick tables and write a single-detail join). To get every column and a snippet per detail level for the few tables you actually need, call again with `tables=["<name>", ...]` (a `name` from the index, e.g. 'education/gosa/attendance' or 'attendance', or a dimension like 'districts'). Paste the `read_parquet(...)` snippets verbatim into your SQL — they are exactly what the sandbox accepts.
Eingabeschema 
{'type': 'object', 'title': 'link_tablesArguments', 'properties': {'tables': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Tables', 'default': None}}}
Ausgabeschema 
{'type': 'object', 'title': 'link_tablesDictOutput', 'additionalProperties': True}
list_datasets
Enumerate every approved Georgia dataset (topic) and the shared dimensions. Each topic entry is a LEAN summary — name/keys, year coverage (year_min/year_max + year_gaps), detail levels + default detail, a has_demographic flag (false = no demographic axis, so there is no all-students demographic row to filter), tags, contract version, and a one-line description — enough to pick a topic; call describe_dataset for its full schema (columns, filters, grain, source, example queries). Each dimension entry carries its primary key, attribute columns, and (for districts) cross-dataset link keys. Call this first to learn what exists — but for a NAMED task (you already know roughly the topic), prefer search_datasets, which returns far fewer bytes than this full catalog.
Eingabeschema 
{'type': 'object', 'title': 'list_datasetsArguments', 'properties': {}}
Ausgabeschema 
{'type': 'object', 'title': 'list_datasetsDictOutput', 'additionalProperties': True}
query_dataset
Query one topic's gold facts with dimension labels joined in (the district/school/county/demographic names come back on every row). `filters` is a dict of column → value or list-of-values: FK codes (district_code, school_code, county_fips, demographic) and any categorical column — see describe_dataset's `filters` for the exact keys and enum values. Use `year` (exact) OR `year_min`/`year_max` (range), never both. `detail` picks the grain (default is the finest available). Returns `rows` plus a `columns` descriptor array (type/role/unit/null-meaning, and `is_key_metric` flagging the headline column) so you interpret values and NULLs correctly — NULL usually means SUPPRESSED, not zero (see null_semantics). The top-level `key_metric` echoes which column is the answer. Use `columns` to project a subset, `include_labels=false` to skip the joined name columns (codes only), and `order_by`+`order` for server-side top-N instead of over-fetching. Pages are small (default 100, max 500); when `truncated` is true a `bulk_export` block points at the REST CSV/Parquet endpoint and the source path for the full pull — do not loop pagination to dump a table. A bad filter returns a self-describing error listing the valid keys/values.
Eingabeschema 
{'type': 'object', 'title': 'query_datasetArguments', 'required': ['topic'], 'properties': {'year': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Year', 'default': None, 'description': 'Exact year. Use this OR year_min/max.'}, 'limit': {'anyOf': [{'type': 'integer', 'minimum': 1}, {'type': 'null'}], 'title': 'Limit', 'default': None, 'description': 'Page size (default 100, max 500).'}, 'order': {'type': 'string', 'title': 'Order', 'default': 'asc', 'description': "Sort direction for order_by: 'asc' or 'desc'."}, 'topic': {'type': 'string', 'title': 'Topic', 'description': "Topic name, e.g. 'act_scores'."}, 'detail': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Detail', 'default': None, 'description': 'Grain (e.g. schools/districts/states); default finest.'}, 'offset': {'type': 'integer', 'title': 'Offset', 'default': 0, 'minimum': 0, 'description': 'Row offset for paging (>= 0).'}, 'columns': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Columns', 'default': None, 'description': 'Project only these output columns (fact columns + joined label columns). Smaller pages / fewer column reads. Omit for all columns.'}, 'filters': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Filters', 'default': None, 'description': "Column â\x86\x92 value (or list of values) filters. Keys are FK columns (district_code, school_code, county_fips, demographic) and categorical columns; read describe_dataset's `filters` for the exact keys and enum values FIRST. A value list is a union (OR); multiple keys AND together. A wrong key/value returns a self-describing error listing the valid ones."}, 'order_by': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Order By', 'default': None, 'description': 'Order by one fact column or joined label column (for server-side top-N). Default order is the row grain. NULL (suppressed) cells sort LAST in either direction, so a metric top-N is never polluted by suppressed rows.'}, 'year_max': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Year Max', 'default': None, 'description': 'Inclusive upper year bound (range).'}, 'year_min': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Year Min', 'default': None, 'description': 'Inclusive lower year bound (range).'}, 'main_topic': {'type': 'string', 'title': 'Main Topic', 'default': 'education', 'description': "Main topic: 'education', 'census', or 'immigration'."}, 'include_labels': {'type': 'boolean', 'title': 'Include Labels', 'default': True, 'description': 'Join district/school/county/demographic name columns (default true); false = codes only (faster, leaner).'}}}
Ausgabeschema 
{'type': 'object', 'title': 'query_datasetDictOutput', 'additionalProperties': True}
resolve_entity
Resolve a place or demographic NAME or CODE to its stable keys + labels — the right way to turn 'Atlanta Public Schools' / 'Fulton' / a raw code into the district_code / school_code / county_fips / demographic to filter by (a wrong code guess otherwise returns an empty query_dataset page). `kind` is district / school / county / demographic ('Fulton' as kind='county' → the county; as kind='district' → the school district — they are different things). Fuzzy-matches and ranks candidates, flags `ambiguous` when several tie, and reads only the small dimension table (no fact scan). A real Georgia place is never matched to a different one: a consolidated city returns its county (matched_on=consolidated_city: 'Columbus' -> Muscogee), another city asked as a county returns the county it lies in flagged ambiguous, and a one-letter misspelling returns matched_on=typo. Read `place_note` and tell the user when it is present.
Eingabeschema 
{'type': 'object', 'title': 'resolve_entityArguments', 'required': ['kind', 'query'], 'properties': {'kind': {'type': 'string', 'title': 'Kind'}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 10}, 'query': {'type': 'string', 'title': 'Query'}}}
Ausgabeschema 
{'type': 'object', 'title': 'resolve_entityDictOutput', 'additionalProperties': True}
search_datasets
Keyword search over the catalog metadata (topic names, descriptions, tags, AND column names/descriptions) — the discovery entry point when you don't know the exact topic name. Returns lean topic summaries per hit with a relevance score and which fields matched, plus a `dimension_matches` list when the query also hits a dimension (e.g. 'district'). Most acronyms work; the short ones `ap`/`el`/`ib` are recognized. Follow up with describe_dataset. `limit` caps results (default 20, max 100).
Eingabeschema 
{'type': 'object', 'title': 'search_datasetsArguments', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 20}, 'query': {'type': 'string', 'title': 'Query'}}}
Ausgabeschema 
{'type': 'object', 'title': 'search_datasetsDictOutput', 'additionalProperties': True}
Verlauf

Letzte Tool-Änderungen

Geändert
aggregate
29. September 2026 02:59
Geändert
describe_dataset
29. September 2026 02:59
Geändert
resolve_entity
27. September 2026 02:50
Hinzugefügt
link_query
17. September 2026 12:54
Hinzugefügt
link_tables
17. September 2026 12:54
Hinzugefügt
get_contract
17. September 2026 12:54
Hinzugefügt
get_dimension
17. September 2026 12:54
Hinzugefügt
describe_dimension
17. September 2026 12:54
Hinzugefügt
resolve_entity
17. September 2026 12:54
Hinzugefügt
aggregate
17. September 2026 12:54
Hinzugefügt
distinct_values
17. September 2026 12:54
Hinzugefügt
query_dataset
17. September 2026 12:54
Hinzugefügt
describe_dataset
17. September 2026 12:54
Hinzugefügt
search_datasets
17. September 2026 12:54
Hinzugefügt
list_datasets
17. September 2026 12:54
Entdecken

Ähnliche MCP-Server

opportunity-exchange

ca.veilpoint/opportunity-exchange

Provides governed Saskatchewan labor-market, wage, housing, community-economy, workforce-pathway, procurement, and business-readi…

Education Data

io.github.pipeworx-io/education-data

Provides US K-12 school and district data, including enrollment, staffing, funding, spending, and child poverty statistics.

Unesco Uis

io.github.pipeworx-io/unesco-uis

Browses and retrieves UNESCO statistics on education, literacy, science, research, and culture.

College Scorecard

io.github.pipeworx-io/college-scorecard

Retrieves college information such as tuition, admissions, enrollment, completion, earnings, and debt from the US College Scoreca…

Analytics Legends — SAP Analytics Intelligence

ai.analyticslegends/sap-analytics

Provides SAP analytics intelligence through searchable firm, market, opportunity, news, concept, study, training, and knowledge-g…

Math MCP Learning

io.github.clouatre-labs/math-mcp-learning-server

Provides mathematical and statistical calculations, matrix operations, unit conversions, educational plots, and persistent calcul…

site

com.gpagradecompare/site

Provides searchable GPA and grade-comparison data with row comparisons, rankings, statistics, provenance, and a human-provider en…

SACS.ai MCP — California School District Financial Data

ai.sacs/sacs-mcp

Queries, compares, and contextualizes official California school district financial datasets and explains public SACS accounting …