# Lumen MCP server

> Gives AI coding agents local semantic code search so they find relevant functions and types without reading entire files.

- Repository: https://github.com/ory/lumen
- Page: https://hostedmcp.org/servers/ory/lumen
- Transport: —
- Stars: 318

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `LM_STUDIO_HOST` | no | no |  |
| `LUMEN_BACKEND` | no | no |  |
| `LUMEN_EMBED_CTX` | no | no |  |
| `LUMEN_EMBED_DIMS` | no | no |  |
| `LUMEN_EMBED_MODEL` | no | no |  |

## FAQ

### Does Lumen send my code to the cloud?

No. Lumen runs fully locally with open-source embedding models, SQLite, and your own CPU, so embeddings never leave your machine.

### How much does Lumen reduce token costs?

Across 9 benchmark runs on 9 languages Lumen cut cost in every language, by up to 39%, while maintaining patch quality.

### Which embedding backends does Lumen support?

It works with either Ollama or LM Studio as the local embedding backend.

### Which languages can Lumen index?

Lumen supports 12 language families including Go, Python, TypeScript, JavaScript, Rust, Ruby, Java, PHP, C/C++, C#, Dart, and Svelte.

### How does Lumen avoid re-indexing unchanged files?

It builds a Merkle tree over file hashes and only re-chunks and re-embeds files that changed.
