> ## Documentation Index > Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # List an intern's connections > Returns the Slack, GitHub, Google Workspace and MCP connections one visible intern can reach, and the shared ones switched off for it or disabled for the workspace. An OAuth grant needs `vault:read`, because the list names members' personal accounts; without it the route answers 403 `insufficient_scope`. The response is sent with `Cache-Control: no-store`. The API key selects the caller, workspace and visible interns. An intern's own API key sees only that intern: the collection and every other intern answer 404 to it. There is no default workspace fallback. Requests on regional hostnames such as `eu.openrouter.ai` are refused. [API key](/docs/api-reference/authentication) required. ## OpenAPI ````yaml /openapi/openapi.yaml get /interns/{internId}/connections openapi: 3.1.0 info: contact: email: support@openrouter.ai name: OpenRouter Support url: https://openrouter.ai/docs description: OpenAI-compatible API with additional OpenRouter features license: name: MIT url: https://opensource.org/licenses/MIT title: OpenRouter API version: 1.0.0 servers: - description: Production server url: https://openrouter.ai/api/v1 x-speakeasy-server-id: production security: - apiKey: [] tags: - description: API key management endpoints name: API Keys - description: Analytics and usage endpoints name: Analytics - description: Anthropic Messages endpoints name: Anthropic Messages - description: BYOK endpoints name: BYOK - description: >- Submit, list, poll, and delete asynchronous batches of inference requests. See https://openrouter.ai/docs/batch-quickstart. name: Batch - description: Benchmarks endpoints name: Benchmarks - description: Chat completion endpoints name: Chat - description: Task classification market-share endpoints name: Classifications - description: Containers endpoints name: Containers - description: Credit management endpoints name: Credits - description: >- Public OpenRouter usage datasets. Data returned by these endpoints is licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/): reuse and republish it, including commercially, with attribution to OpenRouter. name: Datasets - description: Text embedding endpoints name: Embeddings - description: Endpoint information name: Endpoints - description: External Users endpoints name: External Users - description: Files endpoints name: Files - description: Generation history endpoints name: Generations - description: Guardrails endpoints name: Guardrails - description: Images endpoints name: Images - description: >- Create, inspect, update, provision, suspend and delete OpenRouter interns through an API key, and talk to them: the chat route streams OpenAI-compatible completions from one intern, pausing as an `openrouter.provide_input` tool call when the intern needs your permission or an answer. Available to interns programme members; other callers receive 404. See https://openrouter.ai/docs/guides/ori/intern-chat. name: Interns - description: Model information endpoints name: Models - description: OAuth authentication endpoints name: OAuth - description: Observability endpoints name: Observability - description: Organization endpoints name: Organization - description: Presets endpoints name: Presets - description: Private Endpoints endpoints name: Private Endpoints - description: Provider information endpoints name: Providers - description: Rerank endpoints name: Rerank - description: OpenAI-compatible Responses API endpoints name: Responses - description: >- Management endpoints for SCIM group-to-workspace mappings, authenticated with a management key. These are not the SCIM 2.0 connector endpoints for your identity provider. In your identity provider, enter the SCIM endpoint URL shown when you enable provisioning under Settings > Members > SCIM Mappings. See https://openrouter.ai/docs/guides/features/scim-mappings#set-up-provisioning. name: SCIM - description: Speech-to-text endpoints name: STT x-displayName: Transcriptions - description: >- System One endpoints for models such as Jev, compatible with the TypeSafe SDKs. See https://openrouter.ai/docs/guides/community/typesafe-sdk. name: SystemOne x-displayName: System One - description: Text-to-speech endpoints name: TTS x-displayName: Speech - description: >- The catalog of server tools OpenRouter runs on behalf of a model: accepted `tools[].type` spellings per API format, engines and pricing, and which endpoints run each tool natively. See https://openrouter.ai/docs/guides/features/server-tools. name: Tools - description: >- Store host-bound secrets for a workspace or for one intern. Scope is selected by the API key. Responses return metadata only, never secret values. See https://openrouter.ai/docs/guides/ori/vault. name: Vault - description: Video Generation endpoints name: Video Generation - description: Workspaces endpoints name: Workspaces - description: Alpha feature endpoints for Decisions requests name: alpha.decisions externalDocs: description: OpenRouter Documentation url: https://openrouter.ai/docs paths: /interns/{internId}/connections: get: tags: - Interns summary: List an intern's connections description: >- Returns the Slack, GitHub, Google Workspace and MCP connections one visible intern can reach, and the shared ones switched off for it or disabled for the workspace. An OAuth grant needs `vault:read`, because the list names members' personal accounts; without it the route answers 403 `insufficient_scope`. The response is sent with `Cache-Control: no-store`. The API key selects the caller, workspace and visible interns. An intern's own API key sees only that intern: the collection and every other intern answer 404 to it. There is no default workspace fallback. Requests on regional hostnames such as `eu.openrouter.ai` are refused. [API key](/docs/api-reference/authentication) required. operationId: getInternConnections parameters: - description: ID of an intern visible to the authenticated API key. in: path name: internId required: true schema: description: ID of an intern visible to the authenticated API key. example: 7c9e6679-7425-40de-944b-e07fc1f90ae7 minLength: 1 type: string responses: '200': content: application/json: example: data: - account: acts_as: null is_your_account_linked: null note: null scope: workspace id: github is_enabled: true is_intern_only: false kind: github mcp_server_name: null name: GitHub off_reason: null server: null status: reason: null state: connected tool_count: null schema: $ref: '#/components/schemas/InternConnectionList' description: The intern connections. '401': content: application/json: example: error: code: 401 message: Invalid or missing API key schema: $ref: '#/components/schemas/InternLifecycleError' description: Missing, unknown or provisioning API key. '403': content: application/json: example: error: code: 403 message: Forbidden schema: $ref: '#/components/schemas/InternLifecycleError' description: >- The key owner no longer has access, or the request used a regional hostname. '404': content: application/json: example: error: code: 404 message: Intern not found metadata: reason: not_found retryable: false schema: $ref: '#/components/schemas/InternLifecycleError' description: >- The caller is outside the Intern API programme, the intern is hidden, or lifecycle writes are disabled. '408': content: application/json: example: error: code: 408 message: Operation timed out after 10s. Please try again later. metadata: reason: timeout retryable: true schema: $ref: '#/components/schemas/InternLifecycleError' description: >- The request exceeded its route deadline. The deadline quoted in the message is the route's own, so it differs between operations. '500': content: application/json: example: error: code: 500 message: The request could not be completed metadata: reason: internal_error retryable: true schema: $ref: '#/components/schemas/InternLifecycleError' description: >- The request could not be completed. `metadata.reason` says whether to try again: `internal_error` is a transient failure and carries `metadata.retryable: true`, so the same request may be sent again, while `configuration_error` carries `retryable: false` because the next attempt reads the same missing binding or unusable stored credential. security: - apiKey: [] components: schemas: InternConnectionList: properties: data: items: $ref: '#/components/schemas/InternConnection' type: array required: - data type: object InternLifecycleError: additionalProperties: false description: Intern lifecycle request failure. example: error: code: 404 message: Intern not found metadata: reason: not_found retryable: false properties: error: additionalProperties: false properties: code: anyOf: - type: string - type: integer message: type: string metadata: additionalProperties: false properties: reason: type: string retryable: type: boolean required: - reason - retryable type: object required: - code - message type: object required: - error type: object InternConnection: properties: account: properties: acts_as: description: Whose account it acts as, when known. type: - string - 'null' is_your_account_linked: type: - boolean - 'null' note: type: - string - 'null' scope: description: >- `workspace` for a shared connection, `yours` for the key user's personal account, `shared` for a teammate's. enum: - workspace - yours - shared type: string required: - acts_as - is_your_account_linked - note - scope type: object id: description: >- Stable id: the credential id of an MCP server, else the kind (`slack`, `github`, `google`). type: string is_enabled: description: Whether the intern reaches it now. type: boolean is_intern_only: description: Scoped to this intern rather than shared by the workspace. type: boolean kind: enum: - slack - github - google - mcp type: string mcp_server_name: description: >- The name the intern's MCP config keys the server by; null when it is not an MCP server or is off. type: - string - 'null' name: description: Display name. type: string off_reason: description: >- `switched_off` for this intern, `disabled` for the whole workspace; null while on. enum: - switched_off - disabled - null type: - string - 'null' server: properties: host: type: - string - 'null' surface: type: string transport: type: string url: type: - string - 'null' required: - host - surface - transport - url type: - object - 'null' status: properties: reason: type: - string - 'null' state: enum: - connected - needs_reconnect - not_tested - error type: string required: - state - reason type: object tool_count: description: Tools found by the last successful test. type: - integer - 'null' required: - id - kind - name - is_enabled - is_intern_only - off_reason - mcp_server_name - server - status - tool_count - account type: object securitySchemes: apiKey: description: API key as bearer token in Authorization header scheme: bearer type: http ````