Skip to content

MCP tools

The catalogue exposed over agent access at v0.1.0-preview.9: seventeen tools and four resources. The app itself lists them under Settings → Agent access → Tools, which is generated from the same source as the server, so it never drifts.

Asks first means an approval card appears in the app and the agent waits. A denial returns the error denied by user.

Asks first: no. The project the app currently has open. With none open, every tool answers no project is open in Tinspec.

Asks first: no. Environment names and, per environment, the keys of its variables. Values are never returned.

Asks first: no. The API providers in the project, with the ids used by list_endpoints.

Asks first: no. Search the spec-derived endpoints.

ArgumentTypeNotes
providerstringProvider id from list_providers
querystringFree-text match on path, summary, or operationId
tagstring
methodstringe.g. GET
limitinteger1–500, default 50

Endpoint ids handed to agents are <providerId>:<endpointId>.

Asks first: no. One endpoint in full: parameters, body schema, an example body, documented responses, and which auth provider applies. The example body may come from your own successful sends (secret-scrubbed, with {{placeholders}}), in which case the source is stated.

Asks first: no. The hand-authored requests saved in the project’s collections.

Asks first: no. One saved request in full.

Asks first: yes. Send one request. Either a spec endpoint with overrides, or an ad-hoc request object.

ArgumentTypeNotes
endpointIdstringA spec-derived endpoint from list_endpoints
requestobjectAn ad-hoc request — { name?, protocol?, method, url, headers?, query?, body?, auth?, prerunChain? }. method and url required
overridesobjectquery, headers, body, pathVars — applied to endpointId
environmentstringDefaults to the active one
senderstringThe sender to authenticate as

protocol accepts http, grpc, or graphql — the chainable, single-response protocols.

Returns status, headers, body, timing, and test results. Bodies are truncated to the response-size limit (256 KB when unlimited) with bodyTruncated: true.

Approval is requested for every non-GET/HEAD/OPTIONS method, and for safe methods too unless you have opted into letting those through.

Asks first: no. The chains in the project.

Asks first: yes. Run one.

ArgumentType
namestring
inputsobject — chain input variables

The chain is validated before the approval prompt, so an invalid chain fails with the reason rather than asking you to approve something that cannot run.

Asks first: no — it is read-only and writes nothing.

ArgumentTypeNotes
endpointIdstringThe target to set up prerequisites for
reuseprefer | neverprefer (default) references matching saved requests; never generates every step from the spec

Returns a ready-to-save chain plus the steps, anything unresolved, notes, and validation issues. Pass the returned chain to save_chain, edited as needed.

Asks first: yes.

ArgumentTypeNotes
chainobjectThe chain to write
overwritebooleanDefault false; required to replace an existing name

Validated strictly before the approval prompt — against the workspace’s collections and the active environment’s keys, with extraction paths checked against the spec endpoint each node maps back to. A failure lists code: message (node) lines and writes nothing.

Asks first: no.

ArgumentTypeNotes
limitinteger1–500, default 50
methodstring
statusinteger
sincestringISO-8601 timestamp

Asks first: no. One run in full. The request shown is the pre-resolution snapshot.

Asks first: no. Endpoints added, removed, or modified since you last reviewed the spec — the same data as the Spec Changes view.

Asks first: no. Turns a curl command into a request object. Nothing is saved.

Asks first: yes.

ArgumentType
requestobject
folderstring

Writes the request into the project as YAML.

URIContents
tinspec://spec/<providerId>The provider’s OpenAPI document as YAML
tinspec://collection/<file>A collection file
tinspec://response/lastThe most recent response
tinspec://skillThe bundled agent skill — the server’s instructions point here first
  • Environment values. Keys only.
  • Auth tokens. Headers in the returned sentRequest are masked as Bearer ****.
  • The keychain. Not reachable through any tool.

Response bodies do reach the agent — that is the point of the surface — truncated to the response-size limit, with the agent told when truncation happened.

Bridged sends land in run history with source: "mcp" and a source_detail naming the client and tool; chain runs likewise. The Agent activity panel additionally shows every tool call and resource read with timing, outcome, and the approval decision, session-only — SQLite history is the durable record.

No stdio transport, no remote or hosted MCP, no tools for WebSocket, streaming gRPC, or LangGraph runs, no sampling or elicitation, and no tools for editing environments or auth providers.