> ## Documentation Index > Fetch the complete documentation index at: https://docs.streamkap.com/llms.txt > Use this file to discover all available pages before exploring further. # Discover Mcp Tools > Discover available tools from an MCP server. Three callable shapes - see ``DiscoverMcpToolsRequest`` docs for full details: - **Saved-id:** ``{savedConnectionId}`` -> BE reads the stored row and composes headers server-side; the browser never sees the token. ``savedConnectionName`` is accepted as a deprecated alias for one release cycle. - **Inline with masked secret:** ``{serverUrl, headers: {...: "********"}}`` -> BE matches the serverUrl against saved settings and substitutes the stored secret for every masked header value. - **Inline plaintext:** ``{serverUrl, headers}`` - used on first-save "Test" click before the row exists. URL is validated (SSRF guard) on every path. Per-tenant rate limit: 30 req/min -> 429 with ``Retry-After``. A 300s in-process cache (M10) keyed by ``(serverUrl, headers-hash)`` short-circuits repeat calls; ``X-MCP-Cache: hit|miss`` is emitted on every response. Cache hits still consume rate-limit budget - the cache is not a bypass. ## OpenAPI ````yaml /openapi/openapi.json post /agents/mcp/tools openapi: 3.1.0 info: title: Streamkap REST API description: >- The Streamkap REST API allows you to programmatically manage your CDC pipelines, sources, destinations, transforms, and more. Authenticate using a bearer token obtained from the [Access Token](/api-reference/auth/access-token) endpoint with your API client credentials. contact: name: Streamkap Support url: https://streamkap.com/ email: support@streamkap.com license: name: Proprietary version: 2.0.0 servers: - url: https://api.streamkap.com description: Production security: [] tags: - name: Agents description: Create, deploy, and manage Flink-based AI agents. - name: Agents Observability description: >- Read-only views over the MCP audit log: agent rollup, sessions, spans, histograms, external-agent verify. - name: Alerts description: Manage alert subscribers, preferences, and notification credentials. - name: Authentication description: Obtain and refresh access tokens, manage client credentials and roles. - name: Billing description: Retrieve usage metrics, summaries, and export billing data. - name: Consumer Groups description: List, inspect, and reset Kafka consumer group offsets. - name: Dashboard description: Retrieve organisation-level statistics and overview data. - name: Destinations description: Create, configure, and manage data destinations and their lifecycle. - name: Kafka Access description: Manage Kafka users and their access permissions. - name: Logs description: Query and summarise system logs. - name: Pipelines description: Create, configure, and manage CDC pipelines and their lifecycle. - name: Project Keys description: Manage project keys that bundle API credentials and optional Kafka access. - name: Schema Registry description: Browse schema subjects, versions, and retrieve schema definitions. - name: Services description: View and switch service metadata. - name: Sources description: >- Create, configure, and manage data sources, snapshots, and their lifecycle. - name: Tags description: Create, update, and manage resource tags for organisation. - name: Topics description: Browse topic details, statistics, configurations, metrics, and messages. - name: Transforms description: >- Create, deploy, and manage data transforms, unit tests, and implementation details. paths: /agents/mcp/tools: post: tags: - Agents summary: Discover Mcp Tools description: >- Discover available tools from an MCP server. Three callable shapes - see ``DiscoverMcpToolsRequest`` docs for full details: - **Saved-id:** ``{savedConnectionId}`` -> BE reads the stored row and composes headers server-side; the browser never sees the token. ``savedConnectionName`` is accepted as a deprecated alias for one release cycle. - **Inline with masked secret:** ``{serverUrl, headers: {...: "********"}}`` -> BE matches the serverUrl against saved settings and substitutes the stored secret for every masked header value. - **Inline plaintext:** ``{serverUrl, headers}`` - used on first-save "Test" click before the row exists. URL is validated (SSRF guard) on every path. Per-tenant rate limit: 30 req/min -> 429 with ``Retry-After``. A 300s in-process cache (M10) keyed by ``(serverUrl, headers-hash)`` short-circuits repeat calls; ``X-MCP-Cache: hit|miss`` is emitted on every response. Cache hits still consume rate-limit budget - the cache is not a bypass. operationId: discoverMcpTools requestBody: content: application/json: schema: $ref: '#/components/schemas/DiscoverMcpToolsRequest' required: true responses: '200': description: Successful Response content: application/json: schema: additionalProperties: true type: object title: Response Discovermcptools '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - FronteggHTTPAuthentication: [] components: schemas: DiscoverMcpToolsRequest: properties: serverUrl: type: string maxLength: 2048 title: Serverurl default: '' headers: additionalProperties: type: string type: object maxProperties: 32 title: Headers savedConnectionId: anyOf: - type: string maxLength: 100 - type: 'null' title: Savedconnectionid description: >- If set, BE resolves serverUrl + headers from the tenant's saved connection by id savedConnectionName: anyOf: - type: string maxLength: 100 - type: 'null' title: Savedconnectionname description: >- Deprecated - prefer ``savedConnectionId``. Accepted for backward compatibility for one release cycle. additionalProperties: false type: object title: DiscoverMcpToolsRequest description: |- Request body for POST /agents/mcp/tools. Two callable shapes: 1. **Inline** - the caller sends ``{serverUrl, headers}`` directly. Used for the "Test" button on a new connection form before the row has been saved. If any header value is ``MASK_SENTINEL``, the BE substitutes the stored secret for that row (matched by ``serverUrl``) server-side so the decrypted value never reaches the browser. 2. **By saved-id** - the caller sends ``savedConnectionId`` and the BE reads the stored row from ``agent_connections`` and composes headers via ``mcp_header_resolver``. Used when the tenant triggers a re-discover against an existing saved connection - the browser doesn't need to hold the token at all. For MCP connections (which are keyed by ``name`` in storage), the value sent as ``savedConnectionId`` is the connection's stable ``name``. ``savedConnectionName`` is accepted as a deprecated alias for one release cycle so an in-flight FE that hasn't shipped the rename yet keeps working. New callers should send ``savedConnectionId``. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: FronteggHTTPAuthentication: type: http scheme: bearer ````