Custom MCP Server

Integration of custom MCP servers for extended functionality

Hinweis

With Custom MCP Servers, you can integrate your own functionalities into meinGPT. Connect your server via URL and extend the capabilities of your assistants.

For internal or on-premise targets, use the cross-cutting pattern On-Premise Connections.

Server Configuration

To integrate a Custom MCP Server, you need a URL endpoint. There are two transport options:

HTTP Streaming (Recommended)

https://your-server.com/mcp

This method uses HTTP streaming for efficient real-time communication.

Server-Sent Events (SSE)

https://your-server.com/sse

Alternative method using Server-Sent Events for communication.

Available MCP Servers

Here are some specialized MCP servers you can use:

Remotion Video Server

https://remotion.selectcode.de/mcp
  • Video generation and editing
  • Template-based video production
  • Dynamic content integration

Browser Automation Server

https://browser.selectcode.de/mcp
  • Website navigation
  • Form automation
  • Screenshot and PDF creation

Context7 Documentation Server

https://context7.selectcode.de/mcp
  • API documentation search
  • Code examples
  • Library integration

Server Integration

Add Server

Add the server URL in the assistant settings:

  1. Open assistant configuration
  2. Select "Add MCP Server"
  3. Enter the server URL

Choose Transport

Select the appropriate transport mode:

  • /mcp for HTTP Streaming (recommended)
  • /sse for Server-Sent Events

Test Connection

Verify the server connection:

  1. Check server status
  2. Send test request
  3. Validate response

Authentication Options

Custom MCP Servers support three independent authentication mechanisms: static headers, OAuth, and JWT Identity Forwarding. You can combine them, but see the "Precedence" section below if more than one targets the same header.

Static Headers

In the MCP server configuration, add one or more custom HTTP headers (for example Authorization: Bearer <your-token>) under Headers. Use this for servers protected by a static API key, or by a static token at the edge (e.g. a WAF or reverse proxy in front of your MCP endpoint).

OAuth Authentication

Toggle OAuth Authentication to have meinGPT run the OAuth flow for this MCP URL (when the server advertises OAuth support) and use the resulting access token as the Authorization header.

Precedence

If you configure both a static Authorization header and OAuth for the same server, and OAuth successfully connects, OAuth takes over the Authorization header — your static value is not sent. The two options are not mutually exclusive in the configuration UI, so avoid setting both for the same server unless you intend OAuth to take priority once connected. JWT Identity Forwarding is unaffected by this, since it is sent in a separate X-meinGPT-JWT header (see below).

JWT Authentication (optional)

The cross-cutting concept is documented here: JWT Identity Forwarding.

For custom MCP servers, you can enable JWT authentication in the MCP configuration. When enabled, meinGPT sends this additional header on each request:

X-meinGPT-JWT: <signed-jwt-token>

The token includes claims such as:

  • sub (user ID)
  • email
  • username
  • aud (organization ID)
  • organizationName
  • role
  • teams

To verify this token on your server, use the central guide JWT Identity Forwarding or Security & Authentication Proxy.

Best Practices

  • Security: Use HTTPS for all server connections
  • Monitoring: Monitor server performance and availability
  • Error Handling: Implement fallback options for server outages
  • Documentation: Document server-specific functions and parameters

Next Steps

Was this page helpful?