Updated 22 June 2026

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 open source and in public beta. The five steps below run in about a minute — no account, no keys.

Quickstart: from install to the tokens saved

1. Install trovex.
   uv tool install trovexcopy
2. Index your repo.

   Embeds your markdown locally (SQLite + ONNX). About a minute on a typical repo.

   trovex index /path/to/repocopy
3. Ask a question.
   trovex search "how do we roll back a deploy?"copy
4. See the tokens saved.

   trovex returns the single current doc that answers — down to the section — and prints how many tokens that saved versus rereading the top few candidates. That number is the point. Look for the green ≈ N tokens saved this query line that confirms it worked.

5. Add it to Cursor.

   Start the server, then add a trovex entry to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global) and toggle it on in Cursor Settings → MCP.

   trovex servecopy

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

   Or one click (after trovex serve): Add trovex to Cursor.

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.