MCP servers
MCP (Model Context Protocol) connects external tools and data sources. Once a server is configured, its tools appear in the agent resource list and can be selected.
Server types
Section titled “Server types”| Type | Use when | Key fields |
|---|---|---|
| SSE | Remote service that pushes events | Endpoint URL, headers |
| HTTP | Remote request/response service | Endpoint URL, headers |
| WebSocket | Long-lived bidirectional connection | Endpoint URL, headers |
| Stdio | A local executable | Command, arguments, environment |
Remote types need an endpoint URL and optional headers. Stdio needs a command and arguments.
Create a server
Section titled “Create a server”- Open MCP → New server.
- Name it by capability, e.g.
filesystemorinternal-search. - Description: explain what it provides so it is recognisable in the agent editor.
- Type: choose from the table above.
- Connection: URL for remote; command and one-argument-per-line for Stdio.
- Timeout (seconds): raise it for slow tools.
- Save. The platform discovers tools; the list appears in the server details.
Attach to an agent
Section titled “Attach to an agent”Open the Agents editor and tick the server under MCP servers. Unticked servers are never called by that agent.
Connection fails — test/refresh in the server details; verify URL, headers and timeout. For Stdio, confirm the command exists in the runtime.
No tools listed — the server may expose resources but no tools, or the handshake failed. Check logs.
Tool calls time out — raise the timeout, or use an asynchronous task-style tool.
Several agents, one server — configure once and tick it in each agent.