loci
loci is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Cross-session memory and hybrid RAG over your notes and docs. It has 100 GitHub stars, is released under the MIT license and runs locally with uvx loci-rag.
- AI & search
- MIT
- Actively maintained
Install loci
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"loci": {
"command": "uvx",
"args": [
"loci-rag"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio loci -- uvx loci-ragCursor
{
"mcpServers": {
"loci": {
"type": "stdio",
"command": "uvx",
"args": [
"loci-rag"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"loci": {
"type": "stdio",
"command": "uvx",
"args": [
"loci-rag"
]
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
About loci
Two thousand years ago, orators stored their speeches in the rooms of a palace and walked through them to remember. loci does the same for your files. Loci is the method behind every memory palace: place knowledge in locations, recall it by walking the path.
- chromadb
- embeddings
- knowledge-base
- local-first
- mcp
- mcp-server
- obsidian
- rag
- retrieval-augmented-generation
- second-brain
Similar MCP servers
More ai & search MCP servers
Context7
upstash/context7
Up-to-date code docs for any prompt.
AI & searchTypeScriptFunASR
modelscope/FunASR
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
AI & searchPythonBifrost
maximhq/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
AI & searchGoHoncho
plastic-labs/honcho
Memory that reasons: continual learning for stateful agents.
AI & searchPythonSemble
MinishLab/semble
Fast and Accurate Code Search for Agents.
AI & searchPythonExa
exa-labs/exa-mcp-server
Connect AI agents to Exa for web search, content fetching, and multi-step research.
OfficialAI & searchTypeScript
What is loci?
loci is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Cross-session memory and hybrid RAG over your notes and docs. It has 100 GitHub stars, is released under the MIT license and runs locally with uvx loci-rag. The source code is at github.com/IvenKooLab/loci.
How do I install the loci MCP server?
Add the command uvx loci-rag to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is loci free?
The server is open source under the MIT license, so running it is free. It does not declare any required API key.
Is loci actively maintained?
The most recent commit was on Oct 4, 2026. The latest release is v0.6.3, published Oct 4, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.