Updated 22 June 2026

trovex for Roo Code

Roo Code supports remote streamable-HTTP MCP servers natively. Point it at trovex and the agent gets one canonical doc per query, about 60% fewer tokens.

{
  "mcpServers": {
    "trovex": {
      "type": "streamable-http",
      "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 Roo.

   Start the server, then add the entry below to Roo's mcp_settings.json (via the MCP panel) — Roo takes the streamable-http transport with a url — and toggle it on.

   trovex servecopy

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

Roo's MCP transport fields move between releases — if it doesn't connect, check Roo Code's current MCP transport docs.

Why Roo Code users want it

Roo reads files directly, which is exactly what burns tokens when project knowledge is spread across many markdown docs. trovex gives Roo the one canonical doc that answers a query — section-level, with a freshness marker — so it stops opening several files to find the current one. About 60% fewer tokens per lookup, plus a shared write path so what Roo learns is saved once and read back.