Endpoints: 76,849MCP servers: 32,730Payout addresses: 3,825Paid calls: 6,155Letters: 84Defects: 3,894counted 1 min ago
teppi

Server definition

Hash
sha256:a41ff901aecd52ecb1a5099a0a043305f52a45bcf86686a1247a637c33b39583
What it is
What a remote MCP server returned when asked what it offers: 41 tools

The blob, as servednamed by its sha256

{ "instructions": "CoreModels is a schema graph. What you build here exports to JSON Schema, JSON-LD, ShEx, LinkML, SQL, Avro, OWL and vendor artifacts, so structure and relation direction matter.\n\nBefore writing anything, read the full modeling guide: call get_modeling_guide (or read the resource coremodels://guides/modeling). It takes one call.\n\nThe essentials:\n1. Start each session with get_project_summary and get_mixins_and_relation_groups. Match relation groups by label.\n1b. copy_project clones an existing project server-side (node ids preserved); it runs in the background, poll get_job_status until success.\n2. Import before you build. JSON Schema at a URL: import_jsonschema. dbt, Snowflake, BigQuery, Salesforce and 17 other vendors: get_vendor_integration_status, then import_vendor_project. For dbt, send manifest and catalog. Never rebuild a vendor project by hand.\n3. Domain Includes runs Type -> Element (\"this type has this element\"). Range Includes runs Element -> Type/Taxonomy. Controlled List runs Element -> Taxonomy.\n4. Mint random 32-hex ids or GUIDs, never sequential ones.\n5. Rehearse writes with run_code dryRun=true. Check your work: a Type's Domain Includes relations should be outgoing to its Elements.\n6. Large files go by URL (artifactUrls, customFileUrl), never inline.\n7. Questions or feedback humans should see: list_comments reads a project's discussion, add_comment leaves a comment or reply that shows up in the CoreModels app.\n8. Precise read questions (projections, traversals, counts): query_model_graphql — always fetch the schema first with schemaOnly=true; field names are generated from the project's labels.", "tools": [ { "description": "Answers 'what is affected if this concept changes?' for a governed type, element or controlled vocabulary. Returns: where it is used inside the model (blast radius), which vendor estates carry it and by what path, which external standards it is bound to, and which serializations it can be exported as. Read-only — nothing is modified. Useful before editing a vocabulary term or a column's meaning.", "inputSchema": { "additionalProperties": false, "properties": { "concept": { "description": "The governed type, element or taxonomy — by node id, or by label (case-insensitive), e.g. 'order status values' or 'status'.", "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "spaces": { "items": { "type": "string" }, "type": "array" } }, "required": [ "graphProjectId", "concept" ], "type": "object" }, "name": "analyze_concept_impact", "outputSchema": null }, { "description": "Audits vendor artifacts (e.g. a dbt manifest) against the governed CoreModels graph — read-only. Reports coverage (what is/isn't governed, canonical-mapping coverage), drift (fields added/removed/retyped, enum changes, contract flips), and conformance (vendor best-practice rules). errorCount > 0 is the CI-gate fail signal; 'markdown' holds the human-readable report.", "inputSchema": { "additionalProperties": false, "properties": { "artifactUrls": { "additionalProperties": { "format": "url", "type": "string" }, "description": "Artifact name -> URL to fetch it from (for payloads too large to inline).", "type": "object" }, "artifacts": { "additionalProperties": { "type": "string" }, "description": "Artifact name -> raw content. dbt: manifest (required), catalog, semantic_manifest.", "type": "object" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "spaces": { "description": "Optional target space ids.", "items": { "type": "string" }, "type": "array" }, "vendor": { "description": "Vendor connector key, e.g. 'dbt'.", "type": "string" } }, "required": [ "graphProjectId", "vendor" ], "type": "object" }, "name": "audit_vendor_project", "outputSchema": null }, { "description": "Build the source pack for an artifact: a deterministic, sorted extract of the types, elements, taxonomies and relations in scope, plus a stamp with its packHash. Write the artifact only from this pack, then call check_grounding with the pack, the stamp and your output. The packHash is the version pin. Read-only; nothing is stored.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "provenanceNote": { "description": "Optional note stamped into provenance, for example 'pre-product bridge: rendered outside CoreModels from gated output'", "maxLength": 200, "type": "string" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "templateId": { "description": "Template id from list_artifact_templates, e.g. data-dictionary.", "type": "string" }, "typeIds": { "description": "Optional type node ids; omit for every type in scope (optionally within spaceId).", "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" } }, "required": [ "graphProjectId", "templateId" ], "type": "object" }, "name": "build_source_pack", "outputSchema": null }, { "description": "Check whether an artifact is still current. Rebuilds the source pack for the same template and scope and compares its hash with the packHash the artifact was built from. state is current or stale. Pass the old pack too to get a diffSummary of what changed. Read-only.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "pack": { "description": "Optional. The old pack; when given, the response includes diffSummary.", "type": "object" }, "packHash": { "description": "stamp.packHash of the artifact.", "pattern": "^sha256:[a-f0-9]{64}$", "type": "string" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "templateId": { "type": "string" }, "typeIds": { "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" } }, "required": [ "graphProjectId", "templateId", "packHash" ], "type": "object" }, "name": "check_artifact_freshness", "outputSchema": null }, { "description": "Check an artifact output against its source pack (closed world). Every name in output.refs, every *Ref / *Refs value, every `backticked` name and every first cell of a table row must exist in the pack. Returns passed, checked, unresolved [{name, where}] and warnings. If it fails, fix only the listed names (one repair attempt is recommended) and check again. Pass the stamp to prove the pack was not modified. Read-only.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "output": { "description": "Your artifact output. Must follow the template's output contract, including refs.", "type": "object" }, "pack": { "description": "The pack object returned by build_source_pack, unchanged.", "type": "object" }, "stamp": { "description": "Optional. The stamp returned with the pack; its packHash is verified.", "type": "object" } }, "required": [ "graphProjectId", "pack", "output" ], "type": "object" }, "name": "check_grounding", "outputSchema": null }, { "description": "Get information about all mixins in a CoreModels project.\n\nMixins define structured metadata used for mapping models, system integrations, and other extensions.\nMixin values are attached to nodes; use search_nodes with includeMixins to see them, and bulk_create or create_mixin_value to set them.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "core_models_get_mixins_info", "outputSchema": null }, { "description": "Get information about relation groups for a CoreModels project.\n\nUse the relation groups to create a relation between two nodes.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "core_models_get_relation_groups_info", "outputSchema": null }, { "description": "Compare two source packs by id: types, elements, taxonomy terms and relations that were added, removed or changed. Use it as the basis of a change report. Read-only.", "inputSchema": { "additionalProperties": false, "properties": { "fromPack": { "description": "The older pack.", "type": "object" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "toPack": { "description": "The newer pack.", "type": "object" } }, "required": [ "graphProjectId", "fromPack", "toPack" ], "type": "object" }, "name": "diff_source_packs", "outputSchema": null }, { "description": "Export project data as an Avro (.avsc JSON) schema string.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "nodeIds": { "description": "Optional type node ids to export; omit to export all types (optionally scoped to a space).", "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_avro", "outputSchema": null }, { "description": "Export project data in JSON-LD format using a configured export profile.\n\nUse `fetch_json_ld_import_profiles` first to discover the configTypeId. At least one of exportTypes/exportElements/exportTaxonomies/exportDataTypes must be true. Tree-based mode (graphBased=false) requires exactly one nodeId; graph-based mode allows multiple or none.", "inputSchema": { "properties": { "configTypeId": { "description": "JSON-LD export profile id (from fetch_json_ld_import_profiles)", "type": "string" }, "exportDataTypes": { "default": false, "type": "boolean" }, "exportElements": { "default": false, "type": "boolean" }, "exportTaxonomies": { "default": false, "type": "boolean" }, "exportTypes": { "default": false, "type": "boolean" }, "graphBased": { "default": true, "description": "true = graph-based (no root); false = tree-based (requires exactly one nodeId)", "type": "boolean" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "includeSpace": { "default": false, "type": "boolean" }, "nodeIds": { "description": "For tree-based export, exactly one root node id; for graph-based, optional", "items": { "type": "string" }, "type": "array" }, "spaceId": { "description": "Optional space id to filter export data; empty = all spaces", "type": "string" }, "useDefaultType": { "default": false, "type": "boolean" } }, "required": [ "graphProjectId", "configTypeId" ], "type": "object" }, "name": "export_json_ld", "outputSchema": null }, { "description": "Export project data as a JSON Schema string.", "inputSchema": { "additionalProperties": false, "properties": { "configTypeId": { "description": "Export profile id used for the JSON Schema export.", "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "rootNodeId": { "description": "Optional root node id; empty/omitted to export without a fixed root.", "type": "string" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_jsonschema", "outputSchema": null }, { "description": "Export project data as a LinkML (YAML) schema string.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "nodeIds": { "description": "Optional type node ids to export; omit to export all types (optionally scoped to a space).", "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_linkml", "outputSchema": null }, { "description": "Export project schema as an OWL ontology (Turtle): owl:Class per Type, Datatype/ObjectProperty per\nElement with domain/range, rdfs:subClassOf inheritance, cardinality restrictions preserving\nrequired/array-ness, SKOS concept schemes per Taxonomy, and owl:equivalentClass/Property from\ncross-standard mappings. Anything OWL cannot express is reported as '# lossiness:' comments at the\ntop of the document instead of being silently dropped.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_owl", "outputSchema": null }, { "description": "Export the project as an RML mapping document (RML-Core + RML-IO, namespace http://w3id.org/rml/):\none rml:TriplesMap per Type, an rml:logicalSource per source file or table, a subject template from\nthe identifier element, one rml:predicateObjectMap per Element, and joins (rml:parentTriplesMap +\nrml:joinCondition) for type references. Run the result in an RML engine (RMLMapper, morph-KGC,\nSDM-RDFizer) to build a knowledge graph from your data.\n\nGive sourceKind to bind it to real data (csv | json | xml | sql | sql-query); omit it for a\nskeleton with placeholder sources. The document's first line states its fidelity: RUNNABLE,\nTEMPLATE or SKELETON.\n\nClass and predicate IRIs come from each Type's and Element's mapsTo binding. Where a term is not\nbound, the IRI is minted from its name and reported as '# lossiness:' — a mapping built on minted\nIRIs produces a graph that joins to nothing, so bind the terms (bind_ontology_term) before\npublishing the output.", "inputSchema": { "additionalProperties": false, "properties": { "baseIri": { "description": "Namespace subject IRIs are built under, e.g. https://data.example.gov/id", "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "sourceForm": { "description": "shorthand (default) is what RML engines accept today; rml-io is the newer structured source form", "enum": [ "shorthand", "rml-io" ], "type": "string" }, "sourceKind": { "enum": [ "csv", "json", "xml", "sql", "sql-query" ], "type": "string" }, "sourceTemplate": { "description": "Path or table per type, with {type} substituted, e.g. data/{type}.csv", "type": "string" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_rml", "outputSchema": null }, { "description": "Export project data as a ShEx (Shape Expressions) schema string.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "includeCardinality": { "description": "Whether to emit ShEx cardinality markers (?, *, +). Defaults to true.", "type": "boolean" }, "nodeIds": { "description": "Optional type node ids to export; omit to export all types (optionally scoped to a space).", "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_shex", "outputSchema": null }, { "description": "Export project data as a SQL DDL (CREATE TABLE) schema string.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "nodeIds": { "description": "Optional type node ids to export; omit to export all types (optionally scoped to a space).", "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" }, "spaceId": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "export_sql", "outputSchema": null }, { "description": "Fetch JSON-LD import/export profiles available for a project (id and label each).\nPass configTypeId to read that one profile's field mapping instead: every JSON-LD key it knows and what the key imports as - importAs is mixin (target = mixin column id), relation (target = relation group id), newMixin/newRelation (created on import), space, or none (ignored). targetLabel names the mixin column or relation group; isReversed marks a relation read in the opposite direction.", "inputSchema": { "properties": { "configTypeId": { "description": "Optional. A profile id from this tool's list; returns that profile's field mapping.", "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "fetch_json_ld_import_profiles", "outputSchema": null }, { "description": "Fetch JSON Schema import/export profiles available for a project (id and label each).\nPass configTypeId to read that one profile's field mapping instead: every JSON Schema keyword it knows and what the keyword imports as - importAs is mixin (target = mixin column id), relation (target = relation group id), newMixin/newRelation (created on import), space, or none (ignored). targetLabel names the mixin column or relation group; isSpecialKey marks a structural JSON Schema keyword (properties, items, $ref, ...).", "inputSchema": { "properties": { "configTypeId": { "description": "Optional. A profile id from this tool's list; returns that profile's field mapping.", "type": "string" }, "graphProjectId": { "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "fetch_json_schema_import_profiles", "outputSchema": null }, { "description": "Generate Synapse curation-manifest CSV templates from a schema — the tabular companion to the\ntransform_schema synapse export. Two artifacts per type: {name}.manifest.csv (the blank entry grid,\nheader row only, loadable as a Curator RecordSet CSV) and {name}.dictionary.csv (the column\ndictionary: Column, Type, Description, Required, Value Set — followed by a value-set section listing\ntaxonomy terms for dropdown columns). Source formats: jsonschema | shex | avro | jsonld | sql | osi |\nosi-json | owl | linkml | odm. Stateless — the project scopes auth only; nothing is written.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "sourceFormat": { "description": "jsonschema | shex | avro | jsonld | sql | osi | osi-json | owl | linkml | odm", "type": "string" }, "sourceSchema": { "description": "The source schema text.", "type": "string" }, "typeId": { "description": "Generate manifests for this type only (matched by id or label). Omit for every type.", "type": "string" } }, "required": [ "graphProjectId", "sourceFormat", "sourceSchema" ], "type": "object" }, "name": "generate_synapse_manifests", "outputSchema": null }, { "description": "Generates vendor artifacts from the governed CoreModels graph. For dbt: a schema.yml with enforced model contracts — column data types, not_null/unique constraints and tests, accepted_values tests from governed taxonomies, relationships tests from governed references. SMEs change meaning once in CoreModels; engineers get a reviewed contract diff.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "iriInDescription": { "description": "dbt: also append bound ontology IRIs to the column description so persist_docs carries them into the warehouse column comment. Default true; they always ride in meta regardless.", "type": "boolean" }, "layout": { "description": "dbt file layout: 'model' (default) one property file per model colocated with its .sql; 'folder' one file per model directory; 'single' one repo-wide file.", "enum": [ "model", "folder", "single" ], "type": "string" }, "spaces": { "items": { "type": "string" }, "type": "array" }, "targetVersion": { "description": "Vendor dialect/version. dbt: default emits data_tests: (>=1.8); '1.7' emits legacy tests:.", "type": "string" }, "typeNames": { "description": "Restrict generation to these model/type names (empty = everything eligible).", "items": { "type": "string" }, "type": "array" }, "vendor": { "description": "Vendor connector key, e.g. 'dbt'.", "type": "string" } }, "required": [ "graphProjectId", "vendor" ], "type": "object" }, "name": "generate_vendor_artifacts", "outputSchema": null }, { "description": "Get the status of a background job in a project, e.g. the copy started by copy_project or a background import_owl. Returns { jobDetailsId, projectId, type, status, createdAt, lastUpdatedAt } where status is \"inProgress\", \"success\" or \"failed\". Result-bearing jobs (background import_owl) additionally return a 'result' field on success — for OWL imports it carries the type/element/taxonomy counts and the aggregated lossiness. Poll until status is no longer \"inProgress\"; leave a few seconds between polls.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "description": "Id of the project the job belongs to. For copy_project this is the returned (destination) projectId.", "pattern": "^[a-f0-9]{32}$", "type": "string" }, "jobDetailsId": { "description": "The jobDetailsId returned by the tool that started the job.", "minLength": 1, "type": "string" } }, "required": [ "graphProjectId", "jobDetailsId" ], "type": "object" }, "name": "get_job_status", "outputSchema": null }, { "description": "Get the project schema: all mixin definitions and all relation-group definitions.\n\nUse this once at the start of a session to discover the IDs needed by other tools (mixinId, columnId, relationGroupId). Returns compact positional arrays - see the \"format\" field for the layout.\n\nRead get_modeling_guide before your first write - it explains what each relation group means and which direction it runs.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "get_mixins_and_relation_groups", "outputSchema": null }, { "description": "Returns the CoreModels modeling guide (markdown): how to import vs build, what each relation group means and which direction it runs (Domain Includes, Range Includes, Controlled List, Has List Item, Inheritance, Derived From), bulk_create conventions, and how to verify your work. Read it once before your first write in a session.", "inputSchema": { "additionalProperties": false, "properties": {}, "type": "object" }, "name": "get_modeling_guide", "outputSchema": null }, { "description": "Labels and IDs of types, elements, and taxonomies in the project. Each category is paginated independently.\n\nPagination:\n- First call: omit page (defaults to 0).\n- Each category reports page, pageSize and hasMore. Re-request with page+1 for any category whose hasMore is true.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "page": { "default": 0, "description": "0-based page index, applied independently to each category.", "minimum": 0, "type": "integer" }, "pageSize": { "default": 50, "maximum": 250, "minimum": 1, "type": "integer" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "get_project_summary", "outputSchema": null }, { "description": "Lists the registered vendor connectors (dbt, ...) with capabilities and expected artifacts, and — when 'vendor' is given — the project's last-import state for that vendor (when, tool version, artifact versions, fingerprint, counts, governed dataset count).", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "spaces": { "items": { "type": "string" }, "type": "array" }, "vendor": { "description": "Omit to list all registered vendor connectors.", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "get_vendor_integration_status", "outputSchema": null }, { "description": "List the artifact templates (data dictionary, model map, change report, ...). Each template has a family, audiences, formats, a pack recipe and an output contract. Your response for an artifact must follow its output contract; pass includeContract: true to get it. Read-only.", "inputSchema": { "additionalProperties": false, "properties": { "audience": { "enum": [ "engineer", "analytics-engineer", "steward", "research-data-manager", "executive", "compliance-reviewer", "content-engineer", "content-strategist", "information-architect", "ai-engineer", "frontend-developer", "software-developer" ], "type": "string" }, "family": { "enum": [ "documents", "visual", "reports", "engineering", "agent", "media", "content" ], "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "includeContract": { "default": false, "description": "Include each template's output contract (a JSON Schema).", "type": "boolean" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "list_artifact_templates", "outputSchema": null }, { "description": "List the discussion (comments and replies) of a CoreModels project — the same threads users see in the app's grid collaboration panel. Viewer access is required.\n\nComments are anchored by tag sets: a comment left on a grid cell carries that cell's tag ids (node/element/relation ids, sometimes a section label) plus the project id. Omit anchorIds to list the whole project's discussion; pass anchorIds to return only comments anchored to exactly that tag set (the project id is implied — never include it).\n\nReturns { comments, total, returned, truncated }. comments are top-level threads, newest first, each with its replies nested oldest first; every entry has { id, createdBy, createdByName, message, anchorIds, mentionUserIds, parentId, isResolved, createdDate }. Reply to a thread or leave a new one with add_comment (admin endpoint).", "inputSchema": { "additionalProperties": false, "properties": { "anchorIds": { "description": "Optional cell anchor: return only comments whose anchor tag set equals exactly this set. Do not include the project id.", "items": { "pattern": "^[^,_]+$", "type": "string" }, "type": "array" }, "graphProjectId": { "description": "Id of the project whose discussion to read. Viewer access is required.", "pattern": "^[a-f0-9]{32}$", "type": "string" }, "includeReplies": { "default": true, "description": "Nest each thread's replies in the response.", "type": "boolean" }, "includeResolved": { "default": false, "description": "Also return resolved (closed) threads.", "type": "boolean" }, "maxResults": { "default": 50, "description": "Cap on returned top-level threads (newest first); truncated=true when more matched.", "maximum": 200, "minimum": 1, "type": "integer" }, "textContains": { "description": "Optional text filter, matched in comments and replies.", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "list_comments", "outputSchema": null }, { "description": "List the user's CoreModels projects as [id,name,accessLevel] (see the response \"format\" field). Use a returned id as graphProjectId for other tools. Pass searchTerm to filter by name (case-insensitive substring). Set includePublicProjects=true to also include public projects. Set includeAISummary=true to also return each project's saved AI-generated summary and the time it was generated (4th and 5th elements). Paged: page is 1-based; increment page up to the returned totalPages to get all results.", "inputSchema": { "additionalProperties": false, "properties": { "includeAISummary": { "default": false, "description": "When true, each project row includes its saved AI-generated summary (markdown) and the time it was generated as 4th and 5th elements, or null if none has been generated.", "type": "boolean" }, "includePublicProjects": { "default": false, "description": "When true, public projects the user is not a member of are also included.", "type": "boolean" }, "page": { "default": 1, "description": "1-based page number. Increment to page through results up to totalPages.", "minimum": 1, "type": "integer" }, "pageSize": { "default": 50, "maximum": 250, "minimum": 1, "type": "integer" }, "searchTerm": { "description": "Optional case-insensitive substring to filter projects by name.", "type": "string" } }, "type": "object" }, "name": "list_projects", "outputSchema": null }, { "description": "Run a read-only GraphQL query against a CoreModels project's model — the general query escape hatch for precise questions (projections, traversals, counts) that the fixed read tools don't answer. Viewer access is required, same as the app.\n\nThe schema is GENERATED PER PROJECT: field names are camelCased from this project's labels and cannot be guessed. Always call with schemaOnly=true first and write queries against the returned SDL (standard introspection queries also work, but the SDL is far cheaper). Root fields: types, elements, taxonomies, views, exemplars, spaces, mixins, relationGroups. Node roots take filter arguments id, ids, names, spaceId — note `names` is a search expression, not an exact match.\n\nQueries only: the schema has no Mutation or Subscription type. GraphQL variables and operationName are not supported — inline all literals into the query document.\n\nThere is NO pagination and every matched node is returned with all its relations, so select narrowly and always filter. Results whose serialized data exceeds maxChars come back as { truncated: true, totalChars, maxChars, dataPreview } instead of { data } — tighten the query rather than raising maxChars. On a GraphQL error (usually a wrong field name) you get an error result; re-check the schema with schemaOnly=true.", "inputSchema": { "additionalProperties": false, "properties": { "graphProjectId": { "description": "Id of the project to query. Viewer access is required.", "pattern": "^[a-f0-9]{32}$", "type": "string" }, "maxChars": { "default": 100000, "description": "Cap on the serialized result size. The server has no pagination; over the cap you get truncated:true with a string preview instead of data.", "maximum": 500000, "minimum": 1000, "type": "integer" }, "query": { "description": "GraphQL query document (query operations only; no variables — inline all literals). Required unless schemaOnly is true.", "type": "string" }, "schemaOnly": { "default": false, "description": "Return the project's generated GraphQL schema as SDL without executing anything. Call this first: field names are camelCased from this project's labels.", "type": "boolean" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "query_model_graphql", "outputSchema": null }, { "description": "Render a grounded artifact output to text with a provenance footer (templateId, packHash, graphProjectId, builtAt, renderedAt). Formats: md (sections in contract order), mermaid (class diagram drawn from the pack; model-map only), json. With pack and no output, md and mermaid render in degraded mode (no model needed). xlsx, docx and pptx are not supported yet. Read-only; nothing is stored.", "inputSchema": { "additionalProperties": false, "properties": { "format": { "enum": [ "md", "mermaid", "json", "xlsx", "docx", "pptx" ], "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "output": { "description": "The output that passed check_grounding. Optional for degraded mode.", "type": "object" }, "pack": { "description": "Optional. Needed for mermaid and for degraded mode; verified against stamp.packHash.", "type": "object" }, "stamp": { "description": "The stamp returned by build_source_pack.", "type": "object" }, "templateId": { "type": "string" } }, "required": [ "graphProjectId", "templateId", "format", "stamp" ], "type": "object" }, "name": "render_artifact", "outputSchema": null }, { "description": "Execute a JavaScript program that orchestrates this server's tools, and return only its result.\n\nPrefer this over many individual tool calls when a task needs several steps, looping, filtering, or\ncombining data: intermediate results stay in the sandbox, so only what you return reaches the model.\n\nInside the script:\n- listTools() -> [{name, summary}] discover available tools\n- getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs\n- tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it)\n- console.log(...) captured and returned alongside the result\n- return <value> JSON-serialized and returned\n\nEnvironment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements\nand number of tool calls.\nThis endpoint serves read-only tools, so only read tools are ever callable from code here. Code-mode\nwrites (an allowlist of creation tools) are served by the admin endpoint (/mcp-admin).\nUse listTools() to see what is callable right now.", "inputSchema": { "additionalProperties": false, "properties": { "code": { "description": "JavaScript to execute. Use tools.<name>(args), listTools(), getToolDoc(name); end with `return <value>`.", "type": "string" }, "dryRun": { "default": false, "description": "When true, write-tool calls are collected and reported as plannedWrites instead of being executed. Read tools run normally.", "type": "boolean" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" } }, "required": [ "graphProjectId", "code" ], "type": "object" }, "name": "run_code", "outputSchema": null }, { "description": "Get available classification options for SchemaLibrary projects, used to categorize and tag projects. Optionally filter by classification name (partial match supported).", "inputSchema": { "properties": { "nameFilter": { "description": "Filter by classification name (optional - partial match supported)", "type": "string" } }, "type": "object" }, "name": "schema_library_get_classifications", "outputSchema": null }, { "description": "Get available metadata options for SchemaLibrary projects (access methods, types, licenses, formats, domains, audiences, model sizes). Use these IDs when creating or updating projects. Optionally filter by category.", "inputSchema": { "properties": { "category": { "description": "Filter by metadata category (optional)", "enum": [ "AccessMethod", "AccessType", "Audience", "Domains", "Format", "License", "ModelSize", "Type" ], "type": "string" } }, "type": "object" }, "name": "schema_library_get_metadata_options", "outputSchema": null }, { "description": "Get available use case types for SchemaLibrary projects. Use these types when creating new use cases for a project.", "inputSchema": { "properties": {}, "type": "object" }, "name": "schema_library_get_use_case_types", "outputSchema": null }, { "description": "Search and retrieve a filtered, paginated list of SchemaLibrary projects with advanced filtering options including metadata, classifications, and project attributes.", "inputSchema": { "properties": { "accessMethodId": { "type": "string" }, "accessTypeId": { "type": "string" }, "audienceIds": { "description": "Comma-separated audience IDs", "type": "string" }, "classificationIds": { "description": "Comma-separated classification IDs", "type": "string" }, "domainIds": { "description": "Comma-separated domain IDs", "type": "string" }, "formatIds": { "description": "Comma-separated format IDs", "type": "string" }, "graphProjectType": { "description": "Graph project type filter (e.g. 'Public', 'Private')", "type": "string" }, "isExternal": { "type": "boolean" }, "isFeatured": { "type": "boolean" }, "licenseId": { "type": "string" }, "modelSizeId": { "type": "string" }, "onlyFavoriteProjects": { "default": false, "description": "Authenticated only", "type": "boolean" }, "onlyMyProjects": { "default": false, "description": "Authenticated only", "type": "boolean" }, "page": { "default": 1, "minimum": 1, "type": "integer" }, "pageSize": { "default": 10, "maximum": 250, "minimum": 1, "type": "integer" }, "publishState": { "default": "All", "enum": [ "Published", "Unpublished", "All" ], "type": "string" }, "sortBy": { "default": "RecentlyUpdated", "enum": [ "Trending", "RecentlyCreated", "RecentlyUpdated" ], "type": "string" }, "title": { "description": "Search by project title (partial match)", "type": "string" }, "typeId": { "type": "string" } }, "type": "object" }, "name": "schema_library_projects_section", "outputSchema": null }, { "description": "Query and retrieve details of a SchemaLibrary project including metadata, classifications, likes, cover images, and user permissions. Authenticated callers receive additional user-specific data (e.g. ILiked, Role).", "inputSchema": { "properties": { "projectId": { "description": "The SchemaLibrary project ID", "type": "string" } }, "required": [ "projectId" ], "type": "object" }, "name": "schema_library_query_project", "outputSchema": null }, { "description": "Search nodes in a CoreModels project. Returns compact positional arrays; the response \"format\" field describes the layout.\n\nFilters (provide at least one of the first three; they combine with AND):\n- nodeIds: exact id lookup\n- nodeType: one of Element, Type, Taxonomy, Exemplar, Component, Space, Tag, Mixin\n- expression: partial substring match on the node label (plain text, no wildcards)\n- spaceIds: restrict results to specific spaces. Narrowing only - cannot be the sole filter; always combine it with nodeIds, nodeType, or expression.\n\nOptional flags: includeRelations, includeMixins, includeTimestamps, sortAttr, sortDesc, pageSize.\n\nPagination:\n- Page-number based: pass page (1-based) and pageSize (max 250).\n- The response includes the total match count, so more pages exist while page * pageSize < total.", "inputSchema": { "additionalProperties": false, "properties": { "expression": { "description": "Partial substring match against the node label. Plain text only - no wildcards, no regex, no '*', '%', '_' or '?' characters; the literal characters are matched as-is.", "examples": [ "Patient", "Address" ], "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "includeMixins": { "default": false, "type": "boolean" }, "includeRelations": { "default": false, "type": "boolean" }, "includeTimestamps": { "default": false, "description": "Adds creationTime and updateTime (ISO 8601 UTC) to each node. Combine with sortAttr CreationTime/UpdateTime to see when nodes changed.", "type": "boolean" }, "limitPerRelationGroup": { "description": "Only with includeRelations. Caps relations returned PER relation group for each node (e.g. 100). Omit for no cap.", "minimum": 1, "type": "integer" }, "nodeIds": { "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" }, "nodeType": { "enum": [ "Element", "Type", "Taxonomy", "Exemplar", "Component", "Space", "Tag", "Mixin" ], "type": "string" }, "page": { "default": 1, "description": "1-based page number. The response includes 'total' (the total match count) so you can compute how many pages there are.", "minimum": 1, "type": "integer" }, "pageSize": { "default": 50, "maximum": 250, "minimum": 1, "type": "integer" }, "sortAttr": { "enum": [ "Label", "CreationTime", "UpdateTime", "" ], "type": "string" }, "sortDesc": { "default": false, "type": "boolean" }, "spaceIds": { "items": { "pattern": "^([a-f0-9]{32}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})$", "type": "string" }, "type": "array" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "search_nodes", "outputSchema": null }, { "description": "Suggest ontology-term candidates for a schema node from the public EMBL-EBI Ontology Lookup Service\n(OLS). ADVISORY ONLY: this is a read-only search — it calls the external EBI OLS API and returns\nranked candidates, and it NEVER writes anything to the graph. In particular it never sets the\nauthoritative mapsTo mixin; binding a chosen term is a separate, explicit human-directed act via\nbind_ontology_term (you name the exact node and the exact term IRI).\n\nProvide either nodeId (the node's label is used as the query) or a raw label (optionally with a\ndescription). Optionally restrict to a comma-separated list of ontologies (e.g. \"efo,mondo,hp\") and\ncap the number of candidates. Each candidate carries { iri, curie, label, description, ontology, type }\nin the relevance order OLS returns; the iri is what you would pass to bind_ontology_term.", "inputSchema": { "additionalProperties": false, "properties": { "description": { "description": "Optional description text to refine the search ranking.", "type": "string" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "label": { "description": "A raw term label to search for. Provide this OR nodeId.", "type": "string" }, "limit": { "default": 10, "description": "Maximum candidates to return (1-50).", "maximum": 50, "minimum": 1, "type": "integer" }, "nodeId": { "description": "The schema node to ground. Its label is used as the query. Provide this OR label.", "type": "string" }, "ontologies": { "description": "Optional comma-separated ontology ids to restrict to, e.g. 'efo,mondo,hp'.", "type": "string" } }, "required": [ "graphProjectId" ], "type": "object" }, "name": "suggest_ontology_terms", "outputSchema": null }, { "description": "Transform a schema from one format to another through the ARAMAI mapping engine.\nFormats: jsonschema | shex | avro | jsonld | sql | osi | osi-json | owl | linkml | protobuf | odcs | graphql | odm | synapse\n(odm decodes only; osi-json is the OSI coder in its JSON serialization — the form dbt ingests;\nsynapse encodes only — the Sage Bionetworks Synapse draft-07 subset with a registered-schema $id;\nits output is plain JSON Schema, decodable via jsonschema; protobuf is a single proto3 .proto file,\nalias proto; odcs is a Bitol Open Data Contract Standard v3 YAML data contract; graphql is a GraphQL\nSDL type-system document, alias sdl — the universal fallback for importing any CMS content model,\nsince every headless CMS can emit an SDL schema; decode imports the content model and skips the\ngenerated query surface — root operation types, Connection/Edge/PageInfo pagination, filter inputs —\nwith an honest lossiness summary).\nMapping: 'inferred' (label/type matching against a target hint), 'explicit' (a SIA mapping-guide\nJSON: autoMatchByMapsTo, fieldMappings [{sourceElementIds, targetElementIds, transformName}],\ntaxonomyDirectives, drops), or 'ai' (Claude proposes a plan; the same validation gate accepts or\nrejects it — requires a server-configured Anthropic key and Editor/Admin project membership, and\nsends the schemas to the Anthropic API server-side). The response carries the produced schema,\nthe executed plan (replayable), and an honest lossiness ledger of everything the transformation\ncould not preserve.", "inputSchema": { "additionalProperties": false, "properties": { "caseInsensitive": { "description": "Inferred mapping: ignore label case (default true).", "type": "boolean" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "guide": { "description": "For explicit mapping: the SIA mapping guide as JSON text. For ai mapping: optional free-text guidance for the model.", "type": "string" }, "mappingKind": { "description": "inferred (default) | explicit | ai", "type": "string" }, "sourceFormat": { "description": "jsonschema | shex | avro | jsonld | sql | osi | osi-json | owl | linkml | protobuf | odcs | graphql | odm", "type": "string" }, "sourceSchema": { "description": "The source schema text.", "type": "string" }, "synapseName": { "description": "For synapse output: the schema name segment of the $id (default: derived from the root type).", "type": "string" }, "synapseOrg": { "description": "For synapse output: the Synapse Organization name for the $id (default 'example'; org.sagebionetworks is reserved).", "type": "string" }, "synapseVersion": { "description": "For synapse output: the semver segment of the $id (default 0.0.1; Synapse rejects re-registering an existing version).", "type": "string" }, "targetFormat": { "description": "jsonschema | shex | avro | jsonld | sql | osi | osi-json | owl | linkml | protobuf | odcs | graphql | synapse", "type": "string" }, "targetHintFormat": { "description": "Format of the optional target hint schema.", "type": "string" }, "targetHintSchema": { "description": "The schema to map toward. Required for inferred mapping.", "type": "string" }, "vendor": { "description": "For sql output: postgres (default) | mysql | sqlserver.", "type": "string" } }, "required": [ "graphProjectId", "sourceFormat", "sourceSchema", "targetFormat" ], "type": "object" }, "name": "transform_schema", "outputSchema": null }, { "description": "Validate one or more JSON documents against a project's stored JSON Schema.\n\nThe schema is regenerated from the project using the supplied configTypeId (the export profile id) and rootNodeId, then reused for every document - so validating a batch costs barely more than validating one. Pass up to 100 documents per call and chunk anything larger.\n\nResponse:\n- isValid: true only when EVERY document passed.\n- total, validCount: counts over the whole batch.\n- invalid: one entry per failing document, as {index, errors}. Only failures are listed - any index not present passed. index is the 0-based position in the jsonStrings array you sent.\n- A document that is not parseable JSON fails in its own slot; it does not abort the rest of the batch.\n\nSet explain=true to add a plain-English \"- Explanation:\" line to every error, describing what is wrong, where, and how to fix it. The raw structured lines are unchanged either way - use it when a person will read the result, leave it off for machine parsing.", "inputSchema": { "properties": { "configTypeId": { "description": "Profile id used to map mixins/relations to schema keywords", "type": "string" }, "explain": { "default": false, "description": "Add a plain-English explanation to each error alongside the raw structured fields. Use when a person will read the output.", "type": "boolean" }, "graphProjectId": { "pattern": "^[a-f0-9]{32}$", "type": "string" }, "jsonStrings": { "description": "The JSON documents to validate, each serialized as a string. Results reference documents by their 0-based position in this array.", "items": { "type": "string" }, "maxItems": 100, "minItems": 1, "type": "array" }, "rootNodeId": { "description": "Node id used as the root when generating the JSON Schema", "type": "string" }, "spaceId": { "description": "Optional space id to scope the schema", "type": "string" } }, "required": [ "graphProjectId", "rootNodeId", "jsonStrings" ], "type": "object" }, "name": "validate_json", "outputSchema": null }, { "description": "Who is calling: returns the identity and subscription plan of the MCP token in use. No project id needed.\n\nReturns { userId, name, email, organizationId, plan }. plan holds the raw tier and expiry from the token plus the derived limits and permissions the other tools enforce: canWrite (writes allowed at all), sharingAllowed (whether invite_user will work — the app's Share-button rule), isEnterprise (large-project copies), maxProjects and maxNodesPerProject. limitsEnforced reports whether the project-cap and per-project node-cap are currently applied on MCP calls (auto-activates 2026-12-31; sandbox project 8185f7b2bd254d1496c6388cd7dc26e6 exempt). Call it at the start of a session to know your limits before creating or importing.", "inputSchema": { "additionalProperties": false, "properties": {}, "type": "object" }, "name": "whoami", "outputSchema": null } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:a41ff901aecd52ecb1a5099a0a043305f52a45bcf86686a1247a637c33b39583 | sha256sum