LocalFree

loci MCP server

IvenKooLab/loci

Queryable second brain over your scattered notes, docs, PDFs and chat exports: hybrid retrieval (vector + BM25 fused with RRF), section-level citations with an optional claim-by-claim verification pass, and an Obsidian-style wikilink graph — all local, any OpenAI-compatible API or fully offline via Ollama. pip install loci-rag then run loci-mcp.

101 GitHub stars1 forks

Install loci in Claude Code

Claude Code
claude mcp add loci -- uvx loci-rag
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "loci": {
      "command": "uvx",
      "args": [
        "loci-rag"
      ]
    }
  }
}

Frequently asked questions

What does the loci MCP server do?

Queryable second brain over your scattered notes, docs, PDFs and chat exports: hybrid retrieval (vector + BM25 fused with RRF), section-level citations with an optional claim-by-claim verification pass, and an Obsidian-style wikilink graph — all local, any OpenAI-compatible API or fully offline via Ollama. pip install loci-rag then run loci-mcp.

Is the loci MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does loci run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add loci to Claude Code?

Run: claude mcp add loci -- uvx loci-rag

More knowledge, memory & rag MCP servers

View all