The obsidian-notes-rag Model Context Protocol (MCP) server provides seamless integration between AI assistants (such as Claude Desktop, Cursor, and Claude Code) and Local vector store for Obsidian notes with semantic search via MCP server. By connecting this server, your AI agent gains specialized capabilities to inspect, query, and automate tasks within the Memory/Knowledge domain.
Once installed in Claude Desktop or Cursor, try asking your assistant:
Copy the config for your editor. Verify environment variables or setup notes in the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"obsidian-notes-rag": {
"command": "uvx",
"args": [
"obsidian-notes-rag"
]
}
}
}
Or install with pip: pip install obsidian-notes-rag
MCP server and CLI for semantic search over your Obsidian vault — or any folder of linked markdown: an OKF knowledge bundle, a repo's docs tree, a wiki export. The CLI installs as obsidian-rag and as okf-search — same tool, use whichever name fits the corpus. Generates embeddings with OpenAI, Ollama, or LM Studio. Stores vectors locally in sqlite-vec (~200KB, no telemetry, no network calls). Nothing requires Obsidian itself: point --root at any markdown directory and both the semantic