Bear

You can access Bear Notes through this MCP server, which reads from Bear’s SQLite database to let you read notes, search text, and list all tags. This makes it easy to integrate Bear data into your workflows and applications via MCP clients.

How to use

You interact with the Bear MCP Server through an MCP client. Use the available tools to fetch data and perform common queries: get_notes retrieves all notes, get_tags lists every tag, and get_notes_like searches notes by text. Use these tools to build features like note previews, tag-based filtering, and full-text search in your own apps.

How to install

Prerequisites: Node.js, Bear app installed on macOS, and access to Bear’s database.

Step 1: Clone the project and install dependencies.

# Clone the project
git clone https://github.com/akseyh/bear-mcp-server

# Change directory
cd bear-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

Running options

You have two official ways to run the Bear MCP Server from your environment.

Docker (recommended if you want to run the server in a container):

{
  "mcpServers": {
    "bear": {
      "command": "docker",
      "args": [
        "run",
        "-v",
        "/Users/[YOUR_USER_NAME]/Library/Group Containers/9K33E3U3T4.net.shinyfrog.bear/Application Data:/app/db",
        "-i",
        "akseyh/bear-mcp-server"
      ]
    }
  }
}

NPM (run directly from your shell without Docker):

{
  "mcpServers": {
    "bear": {
      "command": "npx",
      "args": [
          "bear-mcp-server"
      ]
    }
  }
}

Available tools

get_notes

Retrieves all notes from Bear, returning the complete collection stored in the linked SQLite database.

get_tags

Lists every tag used across all notes in Bear.

get_notes_like

Searches notes for text that matches the provided query, enabling full-text style lookup across your Bear notes.