bear-mcp-server

ruanodendaal/bear-mcp-server

3.4

If you are the rightful owner of bear-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Bear Notes MCP Server with RAG connects your personal knowledge base to AI systems using semantic search and RAG, enhancing Bear Notes with AI capabilities.

The Bear Notes MCP Server with RAG is designed to integrate AI assistants with your Bear Notes, allowing for a more intelligent and context-aware interaction. By leveraging semantic search and Retrieval-Augmented Generation (RAG), this server enables AI systems to understand the content of your notes beyond simple text matching. The server processes everything locally, ensuring privacy and independence from internet connectivity. It uses the Xenova implementation of transformers.js with the all-MiniLM-L6-v2 model to create vector embeddings of your notes, capturing their semantic essence. This setup allows AI assistants to retrieve relevant notes based on meaning, providing a richer and more informed response. The server is particularly useful for users who want their AI assistants to have a deeper understanding of their personal knowledge base, enhancing productivity and information retrieval.

Features

  • Semantic Search: Enables finding notes based on meaning rather than just keywords.
  • RAG Support: Allows AI assistants to pull in relevant context from notes.
  • Local Processing: Ensures all data processing happens on your machine, maintaining privacy.
  • Graceful Fallbacks: Falls back to traditional search if semantic search is unavailable.
  • Easy Setup: Straightforward installation and configuration process.

Usages

node with MCP configuration

{
  "mcpServers": {
    "bear-notes": {
      "command": "node",
      "args": [
        "/absolute/path/to/bear-mcp-server/src/bear-mcp-server.js"
      ],
      "env": {
        "BEAR_DATABASE_PATH": "/Users/yourusername/Library/Group Containers/9K33E3U3T4.net.shinyfrog.net.bear/Application Data/database.sqlite"
      }
    }
  }
}

docker with Bear Notes

bash
docker run \
  -v /path/to/your/NoteDatabase.sqlite:/app/database.sqlite \
  -e BEAR_DATABASE_PATH=/app/database.sqlite \
  -p 8000:8000 \
  bear-mcp-server

Tools

  1. search_notes

    Find notes that match a query with optional semantic search.

  2. get_note

    Fetch a specific note by its ID.

  3. get_tags

    List all tags used in your Bear Notes.

  4. retrieve_for_rag

    Get notes semantically similar to a query, formatted for RAG.