MCP Server

What is MCP Server?

MCP (Model Context Protocol) was released by Anthropic in early November 2024. It standardizes communication between AI models and external systems, simplifying integration. With OpenAI officially supporting MCP, more and more AI vendors are adopting the protocol.

MCP has two main components: Client and Server. The Client is the AI model consumer — it uses MCP Client to give the model the ability to call external systems. The Server provides and runs those external system integrations.

FastGPT's MCP Server feature lets you select multiple apps built on FastGPT and expose them via MCP protocol for external consumption.

FastGPT supports the Streamable HTTP transport. Self-hosted deployments can also expose the compatible SSE transport through the standalone MCP Server service.

Using MCP Server in FastGPT

1. Create an MCP Server

After logging into FastGPT, open Studio and click MCP Server to access the management page. Here you can see all your MCP Servers and the number of apps each one manages.

You can customize the MCP Server name and select which apps to associate.

2. Get the MCP Server URL

After creating an MCP Server, click Start Using to get the access URL.

3. Use the MCP Server

Use the URL in any MCP-compatible client to call your FastGPT apps — for example, Cursor or Cherry Studio. Here's how to set it up in Cursor.

Open Cursor's settings page and click MCP to enter the MCP configuration page. Click the new MCP Server button to open a JSON configuration file. Paste the integration script from step 2 into the JSON file and save.

Return to Cursor's MCP management page and you'll see your MCP Server listed. Make sure to set it to enabled.

Open Cursor's chat panel and switch to Agent mode — only this mode triggers MCP Server calls. After sending a question about fastgpt, you'll see Cursor invoke an MCP tool (described as: query fastgpt Dataset), which calls the FastGPT app to process the question and return results.

Configure Identity Proxy

Identity proxy lets a caller select the team member who executes an MCP tool. FastGPT checks that member's read permission for the target application and attributes chat and runtime records to that member. Use it when a gateway or shared MCP client sends requests on behalf of different team members.

Prerequisites

• Only a team owner can enable identity proxy for an MCP Server.
• The proxied user must be an active member of the same team and have read permission for the target application.
• The key in the published MCP URL is an execution credential. Do not commit it to public code or share it with unrelated users.

1. Enable identity proxy

Create or edit an MCP Server, turn on Auth proxy in the publishing settings, and save the configuration.

When a request does not include an identity proxy header, the tool continues to run as the MCP Server publisher.

2. Configure the proxy identity headers

Pass the identity in the MCP transport headers, not in the tool arguments. FastGPT accepts these headers:

Either header is sufficient. If you provide both, they must resolve to the same team member.

For MCP clients that support custom headers, add headers to the configuration copied in step 2. This example uses a Streamable HTTP URL and a login username:

{
  "mcpServers": {
    "fastgpt": {
      "url": "https://fastgpt.example.com/api/mcp/app/<MCP_KEY>/mcp",
      "headers": {
        "x-fastgpt-auth-proxy-username": "member@example.com"
      }
    }
  }
}

To use a team member ID, replace headers with:

{
  "x-fastgpt-auth-proxy-tmb-id": "<TEAM_MEMBER_ID>"
}

SSE URLs use the same headers. The SSE service captures the proxy identity when it establishes the connection, so reconnect after changing a header. Streamable HTTP reads the headers for each request.

3. Verify the configuration

Call a published tool from the MCP client. A successful call confirms that the proxied user is still an active team member and has read permission for the target application.

If the tool list loads but a tool call returns an authorization error, check the following:

1. Identity proxy is enabled for the MCP Server.
2. The username or team member ID in the request header is correct.
3. If both headers are present, they identify the same member.
4. The member is still active in the team that published the MCP Server.
5. The member has read permission for the application being called.

The tool list exposes only metadata such as tool names and parameters. FastGPT rechecks team membership and application permission for every tool call.

Self-Hosted MCP Server Setup

Self-hosted FastGPT deployments require version v4.9.6 or higher to use MCP Server.

Update docker-compose.yml

Add the fastgpt-mcp-server service to your docker-compose.yml:

fastgpt-mcp-server:
  container_name: fastgpt-mcp-server
  image: ghcr.io/labring/fastgpt-mcp_server:latest
  ports:
    - 3005:3000
  networks:
    - fastgpt
  restart: always
  environment:
    - FASTGPT_ENDPOINT=http://fastgpt:3000

Update FastGPT Container Environment Variables

Configure SSE_MCP_SERVER_PROXY_ENDPOINT in the FastGPT container. Set it to the client-accessible fastgpt-mcp-server URL without a trailing /. For example:

environment:
  SSE_MCP_SERVER_PROXY_ENDPOINT: https://mcp.fastgpt.cn

Restart FastGPT

Restart FastGPT after changing the environment variable:

docker-compose down
docker-compose up -d

After restarting, the MCP Server option will appear in Studio.