Updated 22 June 2026

trovex for Cline

Cline (the VS Code agent) manages MCP servers from its MCP Servers panel and cline_mcp_settings.json. Add trovex as a remote streamable-HTTP server and the agent gets one canonical doc per query — about 60% fewer tokens.

{
  "mcpServers": {
    "trovex": {
      "type": "streamableHttp",
      "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 Cline.

   Start the server, open Cline's MCP Servers panel → Remote Servers (or edit cline_mcp_settings.json), add the entry below, and enable it.

   trovex servecopy

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

Cline's remote-server field names have changed across releases. If trovex doesn't connect, check Cline's current MCP docs for the exact transport key your version expects.

Why Cline users want it

Cline reads files directly, which is exactly the pattern that burns tokens when project knowledge is spread across many markdown docs. trovex hands Cline 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 Cline learns is saved once and read back later.