trovex for Cursor

Cursor configures MCP servers per project in .cursor/mcp.json. Add trovex there and the agent gets one canonical doc per query instead of rereading the repo — about 60% fewer tokens.

{
  "mcpServers": {
    "trovex": { "url": "http://localhost:8765/mcp" }
  }
}

trovex is in private beta — request access first; the steps below work once you're in.

Setup, step by step

1. Index your repo.
   $ uv run trovex index /path/to/repo
2. Start trovex. It serves MCP over HTTP at http://localhost:8765/mcp.
   $ uv run trovex serve
3. Add the config to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global) — the snippet above.
4. Enable it. Open Cursor Settings → MCP, find trovex, and toggle it on. The trovex tool is now available to the agent.

Field names in MCP clients move between versions — if Cursor doesn't pick it up, check Cursor's current MCP docs for the latest schema.

Why Cursor users want it

Cursor already indexes your codebase, but for your docs it still hands the agent files to sift and a .cursorrules blob that goes stale. trovex serves the one canonical doc that answers a query, with a freshness marker, so the agent reads the current section instead of the most similar stale one — about 60% fewer tokens per lookup, plus a shared write path across sessions.