Preview ontology import

When to use

Use extension__ontology__get_import_preview to inspect how a native JSON, RDF, OWL, or SKOS document maps into logical ontology resources before making any changes. The response contains deterministic proposed resources, a preview ID, an apply_supported flag, and a loss report. This MCP tool remains read only. When apply_supported is true, a person can review and approve the proposal in Studio. See Review agent-drafted definitions. A fresh, direct human sign-in is required to save; the MCP tool cannot apply or publish the proposal. The adapter applies bounded parsing and never fetches remote imports. Treat the input document as untrusted and inspect all reported omissions or approximations before using the proposal.

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 that owns the target definitions.
`document`	string	Yes	The complete interchange document, encoded as a string.
`format`	string	Yes	Values: `native_json`, `rdf`, `owl`, `skos`.
`serialization`	string	Yes	Values: `json`, `turtle`, `json_ld`.
`adapter_version`	string	No	Pin the versioned adapter for reproducible output.
`profile`	string	No	Required for RDF, OWL, and SKOS. See Interchange formats.
`base_iri`	string	No	Required for RDF, OWL, and SKOS: an absolute HTTP(S) IRI ending in `/` or `#`.
`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",
  "format": "native_json",
  "serialization": "json",
  "document": "{\"canonicalization_version\":1,\"ontology_id\":\"ontology_01example\",\"resources\":[{\"kind\":\"ontology_object_type\",\"artifact_id\":\"ontology_object_type_01customer\",\"api_name\":\"customer\",\"definition\":{\"ontology_id\":\"ontology_01example\",\"api_name\":\"customer\",\"object_kind\":\"entity\",\"implements\":[],\"properties\":[{\"api_name\":\"customer_id\",\"is_required\":true,\"is_identifier\":true,\"value_schema\":{\"kind\":\"string\"}}]}}]}",
  "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

When to use

Inputs

Example

Permissions and result