Plan SPARQL ontology query

When to use

Use extension__ontology__get_query_plan to resolve a read-only SPARQL 1.1 SELECT query against one exact immutable ontology release. The response identifies the exact release and manifest digest. It includes the query mode, logical operations, resolved resources, unresolved terms, and diagnostics. Set include_definitions to true only when the caller needs the matching logical definitions in resolved_resources. The tool can evaluate its bounded ontology-metadata subset and return metadata bindings. It never reads object instances, resolves physical bindings, emits SQL, or calls a remote SERVICE. Queries that require instance data remain a logical plan with requires_bindings: true. The exact release is the dataset. Queries that declare FROM or FROM NAMED, non-SELECT operations, unsupported graph patterns, or plans outside the bounds return an error instead of a partial executable result.

Inputs

In search mode, the default, run this tool through mcp__call_read_tool, the runner its run_with names: send the inputs below as its arguments, and put session_id and rationale beside them, not inside. In full mode, open a session with mcp__initialise first and pass its session_id. The authenticated mcp__describe_tools result in search mode, or tools/list response in full mode, is the final check for the tool name and schema available to your account.

Input	Type	Required	Meaning
`ontology_id`	string	Yes	Ontology artifact handle owning the release line.
`release_id`	string	Yes	Exact `rel_…` release ID.
`query`	string	Yes	Read-only SPARQL 1.1 SELECT query. Maximum length: 65,536.
`max_operations`	integer	No	Range: 1–256. Default: `128`.
`include_definitions`	boolean	No	Include matching definitions in the logical plan. Default: `false`.
`rationale`	string	Yes	Why this call advances the user’s task. In search mode, send it beside `arguments` instead.
`session_id`	string	Yes	The session ID returned by `mcp__initialise`. Replace the example value with your own. In search mode, send the `session_id` from `mcp__search_tools` beside `arguments` instead.

Example

The example shows the tool’s arguments in full mode. In search mode, send them, without session_id and rationale, as arguments to mcp__call_tool, with session_id and rationale beside them. Replace the object, release, and session IDs with values you can access.

{
  "ontology_id": "ontology_01example",
  "release_id": "rel_01example",
  "query": "SELECT ?type WHERE { ?type a <http://www.w3.org/2002/07/owl#Class> . } LIMIT 25",
  "max_operations": 128,
  "include_definitions": false,
  "session_id": "mcp_session_<your-session-id>",
  "rationale": "I need this released context to answer the user’s question accurately."
}

Permissions and result

This tool is read-only and uses your authenticated identity and workspace permissions. Check the returned release and digest where present, and inspect truncated on bounded retrieval results before relying on completeness. See Use Ontology with agents for the full workflow and MCP Gateway errors for connection and permission failures.

Get started

Tool references

Plan SPARQL ontology query

When to use

Inputs

Example

Permissions and result