bear-mcp
An MCP server that gives AI assistants read and write access to Bear notes on macOS.
README
bear-mcp
An MCP (Model Context Protocol) server that gives Claude and other AI assistants read and write access to your Bear notes on macOS.
Features
- Read notes directly from Bear's SQLite database (no Bear app required to be open for reads)
- Create notes and append/prepend text via Bear's URL scheme
- Search notes by text or tag
- List all tags
- Open notes in the Bear app
Requirements
- macOS
- Bear installed
- Node.js 18+
Installation
git clone https://github.com/dineshs99/bear-mcp.git
cd bear-mcp
npm install
Usage
Claude Desktop
Add the server to your Claude Desktop config at ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"bear": {
"command": "node",
"args": ["/path/to/bear-mcp/index.js"]
}
}
}
Restart Claude Desktop. You should see Bear tools available in the chat input.
Claude Code
claude mcp add bear node /path/to/bear-mcp/index.js
Tools
| Tool | Description |
|---|---|
get_recent_notes |
Get notes created or modified in the past N days |
search_notes |
Search notes by text query and/or tag |
get_note |
Fetch the full content of a note by ID or title |
get_all_tags |
List all tags in your Bear library |
get_notes_by_tag |
Get all notes with a specific tag |
create_note |
Create a new note (opens in Bear) |
add_text_to_note |
Append, prepend, or replace text in a note |
open_note |
Open a specific note in the Bear app |
Example prompts
- "Summarise my Bear notes from the past 7 days"
- "Find all notes tagged #work and give me a bullet-point summary"
- "Create a Bear note titled 'Meeting Notes' with today's date"
- "Append a summary of our conversation to my note titled 'Project Ideas'"
How it works
Read operations query Bear's SQLite database directly at:
~/Library/Group Containers/9K33E3U3T4.net.shinyfrog.bear/Application Data/database.sqlite
Write operations (create, add text, open) use Bear's x-callback-url API, which requires Bear to be installed and the URL scheme to be available.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。