What is MCP?#
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. LumenFlow supports MCP natively.
Building an MCP server#
An MCP server exposes tools with names, descriptions, and input schemas. When connected, LumenFlow automatically discovers these tools and makes them available to Sidekick. MCP servers can be written in any language that supports HTTP or stdio.
For details on building MCP servers, see the MCP specification.
Connecting your server#
- Deploy your MCP server (any hosting that supports HTTP)
- Go to Settings → Connections → Custom MCP
- Enter the server URL
- LumenFlow discovers available tools automatically
- Configure governance rules for each tool
Tool discovery#
When you connect an MCP server, LumenFlow queries it for available tools and their schemas. These appear in Sidekick's tool palette and can be used in conversations.
Best practices#
- Validate inputs — MCP tools receive user-influenced input
- Return structured data — JSON responses work best
- Handle errors gracefully — return error messages, not stack traces
- Document tools — clear descriptions help Sidekick use them correctly
success MCP servers can be written in any language. The protocol uses JSON-RPC over HTTP or stdio.