trovex for Claude Code

Claude Code already reads a CLAUDE.md and rereads your repo to find context. Point it at trovex instead and it gets one canonical doc per query — about 60% fewer tokens.

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. Register it with Claude Code — the one-liner above, or add it to a project .mcp.json:

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

4. Verify. Run /mcp inside Claude Code — trovex should show connected and expose the trovex tool.

Why Claude Code users want it

A CLAUDE.md is one static file that goes stale and can't route a question to the right doc. trovex keeps many docs canonical and hands Claude Code the single current one that answers — down to the section, with a freshness marker — so it stops rereading files to guess which is the source of truth. Same answers, about 60% fewer tokens per lookup, and a shared write path so what one Claude Code session learns is read back by the next. See trovex vs CLAUDE.md for the full comparison.