Bear App MCP

by sachin-philip

2 207 downloads Not rated yet MIT
GitHub

About

Bear App MCP is a Python-based Machine Control Protocol server that provides a programming interface for Bear, a flexible writing app for notes and prose. It allows MCP-compatible clients to read, filter, and delete notes stored in Bear.

Details

License
MIT

Explore

This MCP provides the following tools to interact with Bear:

1. Get List of Notes
- Retrieve the latest notes sorted by update date
- Specify the number of notes to return
- Returns note titles with their last update timestamps

2. Get Notes by Tag
- Filter notes by a specific tag
- Returns all notes with the specified tag, sorted by update date
- Tags should include the '#' prefix (e.g., '#work')

3. Get Note Summary
- Retrieve the content of a specific note by title
- Returns the first 5 lines of the note's content
- Includes the note's last update timestamp

4. Delete Note
- Delete a specific note by title
- Marks the note as trashed in Bear
- Returns success/failure message

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Bear App MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

1. Python 3.11
2. Install UV curl -LsSf https://astral.sh/uv/install.sh | sh
3. Install Dependancy uv activate && uv install

Add the following to your MCP config:

{
  "mcpServers": {
    "Raindrop": {
      "command": "uv",
      "args": [
        "--directory",
        "<location to project clone>",
        "run",
        "bear.py"
      ],
      "env": {
      }
    }
  }
}

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "bear app mcp": {
            "Raindrop": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<location to project clone>",
                    "run",
                    "bear.py"
                ],
                "env": []
            }
        }
    }
}

McpServers

{
    "Raindrop": {
        "command": "uv",
        "args": [
            "--directory",
            "<location to project clone>",
            "run",
            "bear.py"
        ],
        "env": []
    }
}

A Python-based MCP (Machine Control Protocol) interface for Bear, the beautiful, flexible writing app for notes and prose.

Features

This MCP provides the following tools to interact with Bear:

1. Get List of Notes
- Retrieve the latest notes sorted by update date
- Specify the number of notes to return
- Returns note titles with their last update timestamps

2. Get Notes by Tag
- Filter notes by a specific tag
- Returns all notes with the specified tag, sorted by update date
- Tags should include the '#' prefix (e.g., '#work')

3. Get Note Summary
- Retrieve the content of a specific note by title
- Returns the first 5 lines of the note's content
- Includes the note's last update timestamp

4. Delete Note
- Delete a specific note by title
- Marks the note as trashed in Bear
- Returns success/failure message

Prerequisites

1. Python 3.11
2. Install UV curl -LsSf https://astral.sh/uv/install.sh | sh
3. Install Dependancy uv activate && uv install

MCP Server Configuration

Add the following to your MCP config:

{
  "mcpServers": {
    "Raindrop": {
      "command": "uv",
      "args": [
        "--directory",
        "<location to project clone>",
        "run",
        "bear.py"
      ],
      "env": {
      }
    }
  }
}

License

MIT License - See LICENSE file for details

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.