AI Skill Hub 强烈推荐:LMCP 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
AI工具:LMCP,提供macOS和Windows应用程序的原生访问
LMCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
AI工具:LMCP,提供macOS和Windows应用程序的原生访问
LMCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/lanchuske/local-mcp-releases
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"lmcp": {
"command": "npx",
"args": ["-y", "local-mcp-releases"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 LMCP 执行以下任务... Claude: [自动调用 LMCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"lmcp": {
"command": "npx",
"args": ["-y", "local-mcp-releases"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Let your AI actually use your Mac. Ask ChatGPT, Claude or Cursor to read & reply to your email, manage your calendar, text over iMessage, find your files, and pull data from PDFs — it just does it. It even reaches iMessage and your local apps that the web AIs can't. Tools run on-device — for desktop AIs nothing leaves your Mac; an optional, opt-in encrypted relay lets web AIs reach it. No API keys, free.
curl -fsSL 'https://local-mcp.com/install?ref=github-releases' | bash
Installs in 2 minutes. Auto-configures Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, and Zed. Free — no paid tier yet.
⭐ Like it? Star this repo — it helps others discover LMCP.
<p align="center"> <img src="assets/claude-web-demo.gif" alt="Real recording: Claude.ai on the web creating a note and a reminder on a Mac through LMCP, including the consent dialog" width="700"> </p> <p align="center"><em>Real recording — Claude.ai (web) using a Mac's apps through LMCP's Cloud Relay: ask → tools run → you approve → done. Captured with LMCP's own screen-capture tools.</em></p>
<p align="center"> <img src="assets/claude-tools.png" alt="Claude Desktop showing tools across 20 categories with LMCP" width="700"> </p> <p align="center"><em>Native tools across 20 categories — Mail, Calendar, Teams, Slack, WhatsApp, OneDrive, Microsoft 365, Notes, OmniFocus, ServiceNow, and more</em></p>
<details> <summary>Menu bar app</summary> <p align="center"> <img src="assets/tray-app.png" alt="LMCP menu bar app" width="340"> </p> <p align="center"><em>Status at a glance — all your Mac apps connected</em></p> </details>
---
curl -fsSL 'https://local-mcp.com/install?ref=github-releases' | bash
Auto-detects and configures: Claude Desktop · Claude Code · Cursor · Windsurf · VS Code · Zed
Restart your AI client once. That's it.
Run this in Terminal to completely remove LMCP:
curl -fsSL 'https://local-mcp.com/uninstall' | bash
This stops all background processes, removes the auto-start LaunchAgent, deletes the app and binaries, and cleans up the MCP entries from Claude Desktop, Cursor, and other AI clients. Your emails, calendar, and other data are never stored by LMCP and remain untouched.
---
The things people most often want their AI to reach — and the ones cloud connectors can't:
See all guides at local-mcp.com/guides.
---
Claude.ai and ChatGPT can't reach localhost. Enable Cloud Relay in the menu bar app — a secure WebSocket tunnel routes requests to your local server. Your data is encrypted in transit and never stored.
---
The most technically interesting part: Teams messages are read directly from the local LevelDB cache at:
~/Library/Containers/com.microsoft.teams2/.../IndexedDB/https_teams.microsoft.com_0.indexeddb.leveldb
No Azure AD registration, no tenant admin approval, no OAuth tokens. Just the messages already cached on your Mac.
There are several Mac MCP servers — they optimize for different things. An honest read:
| **LMCP** | Apple-native only (e.g. iMCP) | Cloud aggregators (e.g. Composio) | GUI automation (e.g. Macuse) | |
|---|---|---|---|---|
| Apple apps (Mail, Calendar, iMessage…) | ✅ | ✅ | ⚠️ via cloud APIs | ✅ |
| **Teams / Slack / WhatsApp (local, no API)** | ✅ | ❌ | ⚠️ cloud/OAuth | ❌ |
| Works from **web AIs** (ChatGPT, Claude.ai) | ✅ opt-in relay | ❌ | ✅ | ❌ |
| No API keys / OAuth for local apps | ✅ | ✅ | ❌ | ✅ |
| Runs on your Mac (not the cloud) | ✅ | ✅ | ❌ | ✅ |
Where LMCP is unique: the work & messaging apps most people live in — Microsoft Teams, Slack, WhatsApp, Microsoft 365 — read locally with no API keys, and reachable from web AIs like ChatGPT and Claude.ai. Apple-native-only servers stop at Apple apps; cloud aggregators need OAuth and route your data through their servers.
Full head-to-head with the other Mac-native servers: LMCP vs Macuse vs iMCP — capabilities, pricing and privacy, kept honest and current.
Does LMCP send my data to the cloud? No. The tools run on your own machine and read directly from your installed apps. There is no cloud processing and LMCP's servers never store your data. The optional Cloud Relay is an encrypted tunnel that lets a cloud AI (ChatGPT, Claude.ai, Grok) trigger a tool on your machine — the result is produced locally and the backend doesn't persist tool responses.
Can ChatGPT, Claude, or Cursor read my email, calendar, or Teams without API keys or OAuth? Yes. LMCP exposes them as MCP tools that read your local apps directly — no Microsoft Graph tokens, no Google API keys, no OAuth setup for the data.
How is this different from a cloud automation platform? Cloud automation platforms route your data through their servers. LMCP runs the tools on your computer and returns results straight to your AI, so nothing transits a third-party cloud. Choose LMCP when privacy and local-first matter; choose a hosted platform when you want cloud-hosted multi-step workflows.
How is it different from a cloud MCP connector or a Graph-API integration? Those authenticate against vendor cloud APIs (OAuth tokens, tenant-admin consent). LMCP reads the apps already on your machine — Mail, the local Teams/Slack cache, synced OneDrive — with no API keys and no admin approval for the data.
Can it read Microsoft Teams or Slack without the Graph API or admin tokens? Yes. It reads the Teams and Slack data already cached locally on your machine.
Can my AI read and write local Excel, Word, PowerPoint, or PDF files? Yes — it reads and creates Office documents and reads PDFs locally, without uploading them anywhere.
Does it work on Windows? Not yet — LMCP is macOS-only today. Windows & Linux are on the waitlist at local-mcp.com.
How much does it cost? Free, no paid tier yet — a permanent license, not a 14-day trial, no subscription.
---
LMCP (local-mcp-releases) 是一个旨在为您的 AI 原生应用提供本地数据访问能力的工具。它通过 MCP 协议,打破了云端 AI 与本地应用之间的壁垒,让 Claude、Cursor 等 AI 助手能够安全地读取并操作您设备上的本地应用数据,实现真正的本地化 AI 增强体验。
您可以通过一行命令快速安装 LMCP。在终端执行提供的 curl 命令后,系统会自动检测并配置 Claude Desktop、Claude Code、Cursor、Windsurf、VS Code 及 Zed 等主流 AI 客户端。安装完成后,只需重启您的 AI 客户端即可完成配置。如需卸载,运行指定的 uninstall 命令即可彻底清除后台进程、LaunchAgent 及各客户端中的 MCP 条目。
LMCP 提供了多种极具实用价值的本地连接指南,专注于解决云端连接器无法触达的本地数据问题。例如,您可以利用它实现唯一的 iMessage 读取功能(通过读取本地数据库绕过 API 限制),或者通过单个 MCP server 同时集成 Mail、iMessage 与 Teams 的访问能力,让 AI 能够处理这些私密且分散的本地通信数据。
对于需要使用 Claude.ai 或 ChatGPT 等云端 AI 的用户,LMCP 提供了可选的 Cloud Relay 功能。由于云端模型无法直接访问您的 localhost,您可以通过菜单栏应用开启 Cloud Relay,利用安全的 WebSocket 隧道将请求路由至本地服务器。所有数据在传输过程中均经过加密,且不会被 LMCP 服务器存储。
LMCP 展示了极高的技术实现深度,例如在无需 Microsoft Graph API、Azure AD 注册或 OAuth 令牌的情况下,通过直接读取本地 LevelDB 缓存文件(位于 Teams 的 IndexedDB 路径下),实现了对 Microsoft Teams 消息的直接访问,极大地降低了企业级应用的接入门槛。
针对用户最关心的隐私问题,LMCP 明确表示所有工具均在本地机器运行,直接读取已安装应用的数据,不进行云端处理,且其服务器不会存储任何用户数据。可选的 Cloud Relay 仅作为一个加密隧道,用于允许云端 AI(如 ChatGPT、Claude.ai、Grok)安全地触发本地操作。
高质量的AI工具,提供原生访问
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
总体来看,LMCP 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | local-mcp-releases |
| 原始描述 | 开源MCP工具:LMCP — Give your AI native access to your apps. 189 tools across macOS and Windo。⭐15 · JavaScript |
| Topics | mcpai-toolsapple-silicon |
| GitHub | https://github.com/lanchuske/local-mcp-releases |
| License | NOASSERTION |
| 语言 | JavaScript |
收录时间:2026-06-05 · 更新时间:2026-06-05 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端