trovex Compare Answers Use cases Setup star on GitHub

Updated

Is there an MCP server that serves a repo's docs to coding agents?

Direct answer

Yes, trovex is an MCP server built for this. It indexes a repo's markdown and returns the single current doc for a query, a path:line pointer with a freshness marker, instead of letting the agent reread or sift chunks. It serves the answering section for about 60% fewer tokens per lookup, runs locally, and works with any MCP client.

What makes it different from a generic context server

Most retrieval servers hand back the top-k similar chunks and leave the agent to rank them, with no freshness signal. trovex is opinionated for repo docs: it returns one canonical doc, marks stale and duplicate copies so they're skipped, reads at the section level, and closes the write loop — an agent records what it learns once and the rest read it back. See trovex vs context-hub and vs a vector-DB RAG setup for the contrast.

How it runs

trovex serves MCP over streamable HTTP at http://localhost:8765/mcp. Indexing and embeddings run on your machine — vectors in SQLite, ONNX embeddings. There's no cloud and no API keys, and your code never leaves your machine. Connect it from Claude Code, Cursor, Windsurf, Cline, or any MCP client.

FAQ

Which MCP clients can use it?

Any. trovex serves docs over the Model Context Protocol, so Claude Code, Cursor, Windsurf, Cline, and Zed all read the same canonical answer. Point the client at the local trovex server once and every agent in it can query your docs.

What exactly does it index?

The markdown you point it at: a repo's docs, runbooks, ADRs, design notes. It builds a local index and, for a query, returns the one current doc that answers it with a path:line pointer and a freshness marker, rather than the whole folder.

Does it send my docs to a cloud?

No. trovex runs locally with vectors in SQLite and an on-device embedder, no cloud and no API keys, so your docs and code never leave your machine.

An MCP server for your repo's docs.

trovex is open source and in public beta. Install it and connect it to your agent.

uv tool install trovex

Open source (AGPL-3.0 core, MIT CLIs). Local-first — your docs never leave your machine.