Skip to main content
Everything in Open Index as a context layer is about exposing your brain over MCP. A connector is the reverse: a script in <brain>/connectors/*.py that calls someone else’s MCP server and turns the results into entities.

Where do you get mcp_url?

From whoever runs that server:
  • A hosted vendor MCP server — from their docs (e.g. https://mcp.vendor.com/mcp).
  • Another Open Index brain — its open-index serve URL, i.e. http://host:8080/mcp.
  • A local stdio-only MCP server — not supported here. Connectors speak streamable HTTP/SSE over httpx only. It needs an HTTP endpoint.
The URL must be the full endpoint path — the same one an agent would use.

Running connectors

open-index run tracks last-run times in a gitignored .open_index_state.json, so it decides whether a connector is due — your cron drives the clock.