Skip to main content
Via an MCP server (Model Context Protocol) you connect any external system without msg having to define a fixed interface for it. The agent reads the server’s tools automatically; you decide per agent which of them it may use. This is the most flexible way to connect your own domain logic.
The MCP integration is live: the agent calls your server’s tools for real at runtime.

​
Requirements for the server

Transport

The server must provide the Streamable-HTTP interface of MCP (JSON or SSE responses are detected automatically).

Authentication

Static header auth via Bearer token or API key. OAuth flows are not supported.

​
Adding an MCP server

In the Connectors tab of an agent you choose the type MCP server (generic). You can add this type multiple times – each configured server is its own instance.
1

Enter the base URL

The Streamable-HTTP address of your server, e.g. https://mcp.kunde.de/mcp.
2

Choose authentication

  • Bearer token → sent as Authorization: Bearer <Token>.
  • API key → sent as the header X-API-Key: <Key>.
Secret values are stored encrypted.
3

Read out tools (preview)

Before creating it, the portal reads the server’s available tools live and shows them with name and description. This way you see in advance what the server offers.
4

Enable tools

Selectively activate the tools the agent may use. Only enabled tools are available in the flow.
If the address is unreachable or not a valid MCP server, the portal reports the discovery as an error – nothing is created. Correct the address or credentials and trigger the preview again.

​
Keeping tools up to date

If your server’s tool offering changes, you update the stored list via Update tools. The portal reads out anew and replaces the stored selection.
If an update would remove a tool that is still actively enabled on an agent, it is rejected. First remove the tool from the agent, then update again.

​
Results in the flow

Each MCP tool returns two possible results in the flow that you branch on: The actual domain result (the content the server returns) flows to the agent separately for conducting the conversation.
Treat an MCP server like an external trust boundary: only enable tools the agent really needs, and check the behavior with a test call before you go live.