iMessage MCP
Enables reading the local iMessage database and sending messages through Messages.app on macOS, with both local stdio and remote HTTP access.
README
iMessage MCP
An MCP server that reads the local iMessage database and sends messages through Messages.app on macOS.
It runs over stdio for local use and over HTTP for remote use, so a phone or tablet can reach the same server that the laptop uses. That is the point of the project: the desktop-only iMessage integrations work well, but the desktop is the wrong place — the messages worth acting on arrive while you are away from it.
Status
Early. The read layer is being built; the HTTP transport, auth, and deployment
are not written yet. See docs/scope.md for the design, the measurements behind
it, and what is deliberately deferred.
Requirements
- macOS, with Messages signed in
- Python 3.12+ and uv
- Full Disk Access for the Python interpreter, to read
~/Library/Messages/chat.db
Sending additionally needs permission to control Messages, which macOS prompts for the first time a message is sent.
Development
uv sync --extra test
uv run pytest
The test suite is offline and runs against a synthetic database built from Apple's schema. It never opens the real one, so it works on a machine that has never sent an iMessage.
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。