bear
MCP Server integration for Bear note app
claude mcp add --transport stdio akseyh-bear-mcp-server docker run -v /Users/[YOUR_USER_NAME]/Library/Group Containers/9K33E3U3T4.net.shinyfrog.bear/Application Data:/app/db -i akseyh/bear-mcp-server
How to use
This MCP server provides programmatic access to Bear Notes via the Bear MCP interface. It exposes tools to read your notes, list tags, and search notes by text. Specifically, you can use get_notes to retrieve all notes, get_tags to enumerate all tags used across notes, and get_notes_like to search for notes containing a specified text string. The server runs in a Bear-compatible environment (Docker in the example) and connects to Bear’s SQLite database to fetch data. You can integrate these MCP commands into your workflow or automated tools to pull note data without opening the Bear app directly.
How to install
Prerequisites:
- Docker installed on your system (or adapt to your preferred runner).
- Bear app installed on macOS with its data accessible to Bear’s database path used in the container.
Installation steps (Docker):
- Ensure Docker is running on your machine.
- Create or customize the volume path to Bear’s database location if needed (see the docker example below).
- Start the MCP server using the provided docker configuration.
Example (Docker):
- Use the following command or a docker-compose equivalent to run the server with Bear’s data mounted:
# Replace [YOUR_USER_NAME] with your macOS user name in the volume path
docker run -v /Users/[YOUR_USER_NAME]/Library/Group Containers/9K33E3U3T4.net.shinyfrog.bear/Application Data:/app/db -i akseyh/bear-mcp-server
Alternative (NPM):
- Install Node.js and npm.
- Install the MCP server package globally or locally:
npm install -g bear-mcp-server
- Run the server (if the package provides a CLI) or build as per repository instructions, then start:
npx bear-mcp-server
Note: If you prefer Docker, follow the Docker configuration provided in the repository’s README and adjust the Bear data path as needed.
Additional notes
Tips and notes:
- The MCP server relies on Bear’s SQLite database; ensure the Bear app is installed and its database is accessible to the container if using Docker.
- The provided Docker command mounts Bear’s data folder into /app/db inside the container; adjust the path to match your system if necessary.
- Available MCP tools: get_notes (retrieve all notes), get_tags (list all tags), get_notes_like (search notes by text).
- If you encounter permission or path issues, verify that Bear’s data directory permissions allow access by the container or host process.
- You can switch to the npm/npx approach by using the bear-mcp-server package name in place of the docker setup, if you prefer a Node.js environment.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.