trovex for Zed

Zed keys MCP servers under context_servers. trovex serves over HTTP, so you bridge it with mcp-remote — and the agent gets one canonical doc per query, about 60% fewer tokens.

{
  "context_servers": {
    "trovex": {
      "command": {
        "path": "npx",
        "args": ["-y", "mcp-remote", "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 context server to Zed's settings.json — the snippet above. The mcp-remote adapter proxies trovex's HTTP endpoint into the stdio frames Zed expects (no install; npx fetches it).
4. Use it. Open Zed's agent panel; trovex is available as a context server and exposes the trovex tool.

Zed's MCP support evolves — if a native HTTP option lands, you can drop the bridge. Check Zed's current MCP docs.

Why Zed users want it

Zed is fast and its agent is sharp on code, but for project knowledge spread across many markdown files it still rereads to find the current one. trovex hands Zed the single canonical doc that answers — section-level, with a freshness marker — so it stops opening stale copies. About 60% fewer tokens per lookup, plus a shared write path across sessions.