> ## Documentation Index > Fetch the complete documentation index at: https://docs.narrative.io/llms.txt > Use this file to discover all available pages before exploring further. # Finish connecting an external MCP server > Completes a connection started by `POST /mcp-connections`, after the user has consented and the authorization server has redirected their browser through `GET /mcp-connections/callback`. The Narrative app calls this from its callback page, so normally you don't call it yourself. It is part of the public API because the connection flow can also be driven by an integration that handles the redirect itself. ## What this endpoint actually does 1. Looks up the authorization flow by `state` (400 if unknown or expired). 2. Checks the connection behind that flow belongs to the calling user (404 otherwise). 3. Exchanges the stored authorization code at the server's token endpoint, with the flow's PKCE `code_verifier` and the resource indicator. 4. Validates the new token with a `tools/list` call against the MCP server. 5. Stores the encrypted tokens, flips the connection to `connected`, and consumes the flow. Returns the connection's status view, the same shape as `GET /mcp-connections/{id}`. ## Only the user who started the flow can complete it The `state` is not enough. This endpoint requires a bearer token, and the connection must belong to that token's `company_id` **and** `user_id`. A connection owned by someone else returns 404 — identical to a nonexistent one, so ids can't be probed across users. That is what stops a `state` from being used to capture another user's access token, and it is why the public callback only stores the code instead of exchanging it. A failed exchange leaves the flow in place so it can be retried; a failed `tools/list` validation consumes it, since the token has already been issued. ## Permission `agent_conversations` resource with `write` verb. ## Example ```bash curl -X POST "$API/mcp-connections/complete" \ -H "Authorization: Bearer $TOKEN" \ -H "Content-Type: application/json" \ -d '{"state": "Yk8fQ2Zsb3dTdGF0ZQ"}' ``` ## Common errors | Status | Cause | |---|---| | 400 | `state` is malformed, unknown, or expired | | 400 | the callback has not delivered the authorization code yet | | 400 | the token exchange with the authorization server failed | | 400 | the new token failed the `tools/list` validation against the MCP server | | 404 | the connection does not exist, or belongs to another user | ## OpenAPI ````yaml https://docs-cdn.narrative.io/api-reference/main/openapi.json post /mcp-connections/complete openapi: 3.1.1 info: contact: email: support@narrative.io name: Narrative Support url: https://www.narrative.io termsOfService: https://www.narrative.io/legal/terms-of-service x-logo: url: >- https://cdn.narrative.io/images/company-logos/prod/narrative-logo-text-white.svg backgroundColor: rgb(9, 34, 166) altText: Narrative Logo description: >- The [Narrative Data Collaboration Platform](https://app.narrative.io) API is organized around REST. Our API has predictable resource-oriented URLs, accepts form-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes, authentication, and verbs. The current version is a pre-release beta. It may result in unexpected behavior and there may be breaking changes in future releases up to the 1.0 release. title: Narrative Data Collaboration Platform API version: 2.4.x servers: - url: https://api-dev.narrative.io - url: https://api.narrative.io security: [] tags: - name: Access Rules description: >- Access rules let data providers control who can purchase their data and the terms of purchase. The `access-rules` API allows you to manage access rules for your datasets. Related guides: - [What is an access rule?](https://kb.narrative.io/access-rules) - name: Agent Conversations description: >- Build LLM-driven workflows that can call MCP tools, ask the caller for input, and return structured answers. A conversation pins a model, a system prompt, and a tool catalog. Each run sends the model a user message (or a batch of tool outputs from a previously-paused run); the model decides whether to answer directly, call a server-side tool (resolved by the platform via Model Context Protocol), or call a client-side tool (which pauses the run with `requires_action` and waits for the caller to reply). Related guides: - [Agent Conversations Reference](https://docs.narrative.io/reference/architecture/agent-conversations) - [Error catalog](https://docs.narrative.io/reference/architecture/agent-conversations/errors/conversation-not-found) - name: MCP Connections description: >- Connect external (non-Narrative) MCP servers so agent runs can call their tools with the calling user's own OAuth authorization. A connection is created interactively: `POST /mcp-connections` runs OAuth discovery and Dynamic Client Registration against the server and returns a consent URL; the user authorizes in a browser; the authorization server redirects to `GET /mcp-connections/callback`, which stores the authorization code and sends the browser on to the Narrative app; the app calls `POST /mcp-connections/complete` with the user's own bearer token, which exchanges the code and marks the connection `connected`. That last step is authenticated on purpose. The callback is public — it's a cross-site browser redirect, so no bearer reaches it — so it is not allowed to complete anything. Only the user who started the flow can turn the stored code into a token. Tokens are stored encrypted and used server-side — they are never returned by the API. Once connected, reference the connection by id from an agent run's `mcp_servers[].connection_id`. - name: App Invites description: >- App invites allow applications to create one-time, shareable links on behalf of their users. These links enable users to invite third parties who do not have a Narrative account to perform actions within the application. For example, a Narrative user can send an invite link to a third party who then completes a Pinterest OAuth flow and creates a connector profile in the inviter's account, allowing the inviter to deliver audience data to the third party's Pinterest account without the third party needing a Narrative account. This API is intended to be used by applications (via app client credentials) to create and manage invites on behalf of their users, which can then be shared with invitees. - name: Apps description: >- Apps are applications bundled with a UI that can perform various actions on behalf of a user utilizing the Narrative API. Related guides: - [Building a Narrative Native App](https://www.narrative.io/knowledge-base/how-to-guides/building-a-narrative-native-app) - name: Access Tokens description: API Access Token management - name: Attributes description: >- An attribute models a standardized data point available for sale on the Narrative marketplace. Narrative automatically turns data points from provider datasets into attributes so that buyers can purchase well-formed, standardized data from any supplier on the marketplace. - name: Auth description: >- API token is a crucial step for developers to securely authenticate requests to the Narrative API Related guides: - [How to Create an API Token](https://www.narrative.io/knowledge-base/how-to-guides/understanding-narratives-apis/create-an-api-token) - name: Authentication description: User login and registration - name: Billings description: Used by Narrative internally to bill customers - name: Companies description: A collection of employees - name: Company Marketing Information description: Useful information related to companies - name: Compute Pools description: >- Compute pools represent compute resources (e.g. Snowflake warehouses) provisioned within a data plane. Companies can manage and share compute pools, assign them to jobs, and set a default compute pool on data planes. - name: Connections description: Associations between connectors and datasets - name: Data Shops description: |- Self-hosted website to sell your data Related guides: - [Setting up your datashop](https://www.narrative.io/knowledge-base/how-to-guides/shop-builder/settting-up-your-data-shop) - name: Data Streams description: >- The `data-stream` API endpoints allows one to create and update data-streams. Additionally the endpoints allow finding data-streams using free text search. A few of the endpoints are behind authorization. Update endpoint allows a client to post an edited data-stream document as is, without having to change its shape. The API ensures that only certain fields are allowed to be modified. Attempts to modify fields not up for client modifications are ignored. Related guides: - [What is a data stream?](https://kb.narrative.io/what-is-a-data-stream) - name: Contracts description: Contracts related APIs - name: Datasets description: >- Any kind of data, in any schema, can be pushed into the Narrative Data Collaboration Platform as a dataset exactly as it is stored in your own system. The `datasets` API allows you to manage your datasets. - name: Derivations description: >- Derivation rules describe how the value of one Rosetta Stone attribute can be computed from another — for example, hashing a raw email into a SHA-256 hashed email. Each rule carries a transformation expression that reads the source attribute's value through `$source`. The `derivations` API allows you to browse the rules your company can use — the ones it owns plus the ones shared with it through collaborators. Creating and changing them requires an `admin` grant on `attribute_derivations`, and a rule can only be changed by the company that owns it. - name: Destinations description: >- Destinations associate a subscription to a profile. Optionally, ad-hoc quick settings can be configured to a destination. Those quick settings have to match the format defined on the app manifest. - name: Installations description: Installations of Applications for a profile - name: Jobs description: >- Jobs represent an operation done on a given data plane. All jobs today are tied to a query that represents a forecast or a materialized view. The jobs API provides an interface for interacting with the jobs table, which stores various operations involving reading or writing data. This API allows users to retrieve detailed information about specific jobs, including NQL forecasts and materialized views. - name: Mappings description: >- A mapping is a transformation from a dataset to an attribute. Defining a mapping between a dataset and an attribute makes the dataset eligible to participate in subscriptions where a buyer is purchasing the target attribute. - name: Model Inference description: Model Inference - name: Model Training description: >- Train machine learning models on datasets, e.g. text classifiers used to power attribute mappings. - name: Models description: >- Machine learning models for training and inference. Models can be stored in HuggingFace or Narrative repositories and have configurable collaborator permissions for training and inference access. The `models` API allows you to list, retrieve, and update models accessible to your company. - name: NQL description: >- Narrative Query Language (NQL) is a specialized, SQL-inspired language designed to query and manipulate data within the Narrative platform. While it looks and feels much like standard SQL, it offers extended functionality and syntax that let you leverage platform-specific features—such as referencing datasets by their IDs, creating materialized views, or generating forecasts—without having to manage the complexities of different query engines behind the scenes. NQL queries can ultimately compile down to multiple underlying engines (e.g., Snowflake, Spark) to execute your requests efficiently in the Narrative ecosystem. - name: Payment Methods description: Payment methods used to purchase data - name: Products description: Internal routes used to offer datastream as products - name: Profiles description: >- App profiles are associated with an installation. They represent a reference to a configuration that the app can use to save confidential information outside of Narrative's control. Profiles are currently used to configure settings for connector apps. - name: Resources description: >- Narrative gives you access to managed resources, like your own AWS S3 bucket, so that you can effortlessly buy and sell data on the platform. The `resources` API allows you to manage your resources. - name: Schema Inference description: >- The `schema-inference` API analyzes submitted files to automatically infer and return their structure as a dataset schema. - name: Schema Presets description: >- The `schema-presets` API allows you to list the available schema presets, get detailed information about a specific one and manage its life cycle. You can create a schema preset from scratch or create one based on an existing one, administrators can create platform wide available (public) schema preset. - name: Subscriptions description: >- In the Narrative Data Collaboration Platform a subscription represents a set of rules dictating the commercial terms related to the licensing of data. The `subscriptions` API allows you to set and get information about `subscription` objects owned by the authenticated account. - name: Uploads description: >- The `uploads` API allows you to send files to Narrative and use them to perform tasks like creating a list or adding data to a dataset. - name: Usage description: >- The `usage` API enables the recording of usage events associated with a product. - name: Workflows description: >- The `workflows` API allows you to create, schedule, trigger, and archive workflows. Workflows are defined using a serverlessworkflow YAML specification. paths: /mcp-connections/complete: post: tags: - MCP Connections summary: Finish connecting an external MCP server description: >- Completes a connection started by `POST /mcp-connections`, after the user has consented and the authorization server has redirected their browser through `GET /mcp-connections/callback`. The Narrative app calls this from its callback page, so normally you don't call it yourself. It is part of the public API because the connection flow can also be driven by an integration that handles the redirect itself. ## What this endpoint actually does 1. Looks up the authorization flow by `state` (400 if unknown or expired). 2. Checks the connection behind that flow belongs to the calling user (404 otherwise). 3. Exchanges the stored authorization code at the server's token endpoint, with the flow's PKCE `code_verifier` and the resource indicator. 4. Validates the new token with a `tools/list` call against the MCP server. 5. Stores the encrypted tokens, flips the connection to `connected`, and consumes the flow. Returns the connection's status view, the same shape as `GET /mcp-connections/{id}`. ## Only the user who started the flow can complete it The `state` is not enough. This endpoint requires a bearer token, and the connection must belong to that token's `company_id` **and** `user_id`. A connection owned by someone else returns 404 — identical to a nonexistent one, so ids can't be probed across users. That is what stops a `state` from being used to capture another user's access token, and it is why the public callback only stores the code instead of exchanging it. A failed exchange leaves the flow in place so it can be retried; a failed `tools/list` validation consumes it, since the token has already been issued. ## Permission `agent_conversations` resource with `write` verb. ## Example ```bash curl -X POST "$API/mcp-connections/complete" \ -H "Authorization: Bearer $TOKEN" \ -H "Content-Type: application/json" \ -d '{"state": "Yk8fQ2Zsb3dTdGF0ZQ"}' ``` ## Common errors | Status | Cause | |---|---| | 400 | `state` is malformed, unknown, or expired | | 400 | the callback has not delivered the authorization code yet | | 400 | the token exchange with the authorization server failed | | 400 | the new token failed the `tools/list` validation against the MCP server | | 404 | the connection does not exist, or belongs to another user | operationId: completeMcpConnection requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CompleteMcpConnectionRequest' responses: '200': description: >- Connection completed. Returns the status view, normally with `status: connected` and the access token's `expires_at`. content: application/json: schema: $ref: '#/components/schemas/McpConnectionSummary' '400': description: >- The `state` is malformed, unknown, or expired; the authorization code has not arrived yet; or the token exchange / connection validation against the external server failed. See the common-errors table above. content: application/json: schema: $ref: '#/components/schemas/RFCError' '401': description: Missing or invalid bearer token. '403': description: Token does not have `agent_conversations:write` permission. '404': description: No such connection, or it belongs to another user. content: application/json: schema: $ref: '#/components/schemas/RFCError' security: - BearerAuth: [] components: schemas: CompleteMcpConnectionRequest: description: >- Body for `POST /mcp-connections/complete`. The `state` identifies the authorization flow to finish; the authorization code itself is already held server-side and is never sent by the client. type: object required: - state properties: state: type: string maxLength: 512 description: >- The one-time state issued by `POST /mcp-connections` and forwarded to the app by `GET /mcp-connections/callback`. Consumed once the connection completes. example: Yk8fQ2Zsb3dTdGF0ZQ McpConnectionSummary: description: >- Status view of one connection. Deliberately credential-free — the registered client secret and the encrypted access/refresh tokens are never returned. type: object required: - connection_id - server_url - alias - authorization_server - status - created_at - updated_at properties: connection_id: type: string format: uuid example: b3f1c2a4-5d6e-47f8-9a0b-1c2d3e4f5a6b server_url: type: string format: uri description: The external MCP server this connection targets. example: https://huggingface.co/mcp alias: type: string example: huggingface authorization_server: type: string format: uri description: The OAuth issuer discovered for the server. example: https://huggingface.co status: type: string enum: - pending - connected - error description: >- Lifecycle. `pending` after creation, and while waiting on the user's consent and the completion call; `connected` once the token exchange succeeds and `tools/list` validates; `error` for a failed connection. example: connected expires_at: type: - string - 'null' format: date-time description: >- When the current access token expires, if the server issued an expiry. The platform refreshes it automatically before use when a refresh token is available. example: '2026-07-12T18:30:00Z' created_at: type: string format: date-time example: '2026-07-12T17:00:00Z' updated_at: type: string format: date-time example: '2026-07-12T17:02:11Z' RFCError: description: >- RFC 7807 Problem Details. Returned with `Content-Type: application/json` for every 4xx/5xx response on `/agents/*`. **Field semantics:** - `type` — stable URL to the docs page describing this error class. Treat it as the machine-readable identifier; the same URL is referenced by `RunError.docs_url` on failed runs. Optional on 500 errors that don't map to a documented class. - `title` — short human-readable summary. - `status` — HTTP status code echoed in the body (so clients that read only the body can still dispatch on status). - `detail` — request-specific detail. Includes which alias was malformed, which `tool_use_id` was missing, etc. - `instance` — the API surface group (`/agents` for all agent endpoints). Stable — it's the prefix you call, not the full path. - `log_id` — UUID correlated with server logs. Always include this when reporting an issue to support. - `debug` — usually `null`. Reserved for richer payloads in specific failure modes. Common error pages indexed by `type`: | HTTP | Common cause | Docs page | |------|--------------|-----------| | 400 | Bad request body, validation failure | various — see `type` | | 404 | Resource not found, or owned by a different company | `/conversation-not-found`, `/agent-run-not-found` | | 409 | Conversation version moved while you were preparing the run, or another run on it is still in flight | `/version-conflict`, `/run-in-progress` | | 500 | Internal error (schema drift, workflow start failure) | `/invalid-stored-field`, `/workflow-start-failed` | type: object required: - title - status - log_id properties: type: type: - string - 'null' format: uri example: >- https://docs.narrative.io/reference/architecture/agent-conversations/errors/invalid-tool-alias title: type: string example: Invalid Tool Alias status: type: integer example: 400 detail: type: string example: >- invalid tool aliases (must match ^[a-zA-Z][a-zA-Z0-9]{0,7}$): with_underscore instance: type: string example: /agents log_id: type: string format: uuid example: 1f6e5d4c-3b2a-1098-7654-3210fedcba98 debug: type: - object - 'null' example: type: >- https://docs.narrative.io/reference/architecture/agent-conversations/errors/invalid-tool-alias title: Invalid Tool Alias status: 400 detail: >- invalid tool aliases (must match ^[a-zA-Z][a-zA-Z0-9]{0,7}$): with_underscore instance: /agents log_id: 1f6e5d4c-3b2a-1098-7654-3210fedcba98 debug: null securitySchemes: BearerAuth: type: http scheme: bearer ````