此 MCP 可以做什么
Retrieves cited passages from versioned public datasets and supports owner-approved proposals, revisions, deletions, and history tracking.
工具
输入模式
{'type': 'object', 'required': ['revision_id', 'decision'], 'properties': {'note': {'type': 'string', 'description': 'Optional review note'}, 'decision': {'enum': ['approved', 'rejected'], 'type': 'string'}, 'revision_id': {'type': 'string', 'description': 'Revision id returned by koskamo_propose_revision or koskamo_list_revisions'}}}
输出模式
{'type': 'object'}
输入模式
{'type': 'object', 'required': ['dataset'], 'properties': {'dataset': {'type': 'string', 'description': 'Dataset id or slug'}}}
输出模式
{'type': 'object'}
输入模式
{'type': 'object', 'properties': {}}
输出模式
{'type': 'object', 'required': ['datasets'], 'properties': {'datasets': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'slug', 'name', 'description', 'visibility', 'version', 'documentCount', 'createdAt'], 'properties': {'id': {'type': 'string', 'format': 'uuid'}, 'name': {'type': 'string'}, 'slug': {'type': 'string'}, 'license': {'type': 'string', 'description': 'Reuse information, when supplied; consult the original source'}, 'version': {'type': 'integer', 'description': 'Increments every time a document write goes live'}, 'readOnly': {'type': 'boolean', 'description': 'Application-maintained reference datasets do not accept API revisions'}, 'createdAt': {'type': 'string', 'format': 'date-time'}, 'publisher': {'type': 'string', 'description': 'Publisher attribution, when supplied'}, 'reviewedAt': {'type': 'string', 'format': 'date-time', 'description': 'Editorial review date, when supplied'}, 'visibility': {'enum': ['public', 'private'], 'type': 'string'}, 'description': {'type': 'string'}, 'documentCount': {'type': 'integer'}}}}}}
输入模式
{'type': 'object', 'required': ['dataset'], 'properties': {'dataset': {'type': 'string'}}}
输出模式
{'type': 'object'}
输入模式
{'type': 'object', 'required': ['dataset'], 'properties': {'text': {'type': 'string', 'description': 'The improved document text; required unless action is delete_document'}, 'title': {'type': 'string', 'description': 'Required unless action is delete_document'}, 'action': {'enum': ['add_document', 'replace_document', 'delete_document'], 'type': 'string', 'description': 'Defaults to add_document. delete_document needs only dataset and document_id.'}, 'dataset': {'type': 'string', 'description': 'Dataset id or slug'}, 'rationale': {'type': 'string'}, 'source_url': {'type': 'string'}, 'document_id': {'type': 'string', 'description': 'Set to replace or delete an existing document'}, 'restore_version': {'type': 'integer', 'minimum': 1, 'description': 'With replace_document and document_id, propose reverting the document to this stored version; title/text are taken from the version history.'}}}
输出模式
{'type': 'object'}
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'maxLength': 2000, 'minLength': 1, 'description': 'The question or search string'}, 'top_k': {'type': 'integer', 'maximum': 12, 'minimum': 1}, 'dataset': {'type': 'string', 'description': 'Optional dataset id or slug. Defaults to all public datasets.'}}}
输出模式
{'type': 'object', 'required': ['query', 'passages'], 'properties': {'query': {'type': 'string'}, 'passages': {'type': 'array', 'items': {'type': 'object', 'required': ['text', 'score', 'datasetId', 'datasetSlug', 'datasetName', 'datasetVersion', 'documentId', 'documentTitle', 'documentVersion', 'sourceUrl', 'chunkId', 'ordinal', 'version', 'createdAt'], 'properties': {'text': {'type': 'string'}, 'score': {'type': 'number', 'description': 'Ranking score within the retrieval engine; not a confidence probability'}, 'chunkId': {'type': 'string', 'description': 'Chunk uuid for database-backed datasets; dataset:document:ordinal for the bundled catalog'}, 'ordinal': {'type': 'integer', 'description': 'Chunk position inside the source document'}, 'version': {'type': 'integer', 'description': 'Alias of datasetVersion kept for existing citers'}, 'createdAt': {'type': 'string', 'format': 'date-time', 'description': 'Document creation timestamp'}, 'datasetId': {'type': 'string'}, 'sourceUrl': {'type': 'string'}, 'documentId': {'type': 'string'}, 'datasetName': {'type': 'string'}, 'datasetSlug': {'type': 'string'}, 'documentTitle': {'type': 'string'}, 'datasetVersion': {'type': 'integer', 'description': 'Dataset version at retrieval time; cite this'}, 'documentVersion': {'type': 'integer', 'description': 'Document content version; increments when an approved revision replaces the document'}}}}}}
近期工具变更
类似的 MCP 服务器
Stable Baseline
Manages company documents, knowledge graphs, whiteboards, projects, plans, tasks, teams, and improvement workflows.
Dayze — Life Context
Provides authenticated personal life-context data and tools for contacts, memories, events, expenses, trips, assets, places, and …
YouSpot
Connects personal contacts, companies, notes, files, CRM records, email, Slack, LinkedIn, and calendars, with search, relationshi…
cypher-mcp
Provides named Cypher graph queries and code-orientation tools for tracing capabilities, symbols, invariants, provenance, changes…
mcp
Manages Nestr workspaces, roles, circles, tensions, governance proposals, comments, daily plans, graph relationships, agents, and…
HiveLearn
Creates and manages courses, lessons, quizzes, enrollments, learning tracks, events, certificates, resources, progress, and commu…
concordance
Provides deterministic claim verification and audit receipts, along with Bible references, commentary, geography, indexed knowled…
canton-ccpedia
Searches and explains Canton Network and Daml documentation, governance proposals, forums, code examples, APIs, releases, and eco…