Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
作者提供的说明(英文原文)
Unofficial Telegram MCP server — read, search, reply and react in your own Telegram account.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
TELEGRAM_API_ID, TELEGRAM_API_HASH标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.mcp-telegram.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"telegram": {
"command": "npx",
"args": [
"-y",
"@overpod/mcp-telegram"
],
"env": {
"TELEGRAM_API_ID": "your-value",
"TELEGRAM_API_HASH": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http telegram https://mcp.mcp-telegram.com/mcpclaude mcp add telegram --env TELEGRAM_API_ID=your-value --env TELEGRAM_API_HASH=your-value -- npx -y @overpod/mcp-telegram运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"telegram": {
"url": "https://mcp.mcp-telegram.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"telegram": {
"command": "npx",
"args": [
"-y",
"@overpod/mcp-telegram"
],
"env": {
"TELEGRAM_API_ID": "your-value",
"TELEGRAM_API_HASH": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"telegram": {
"type": "http",
"url": "https://mcp.mcp-telegram.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"telegram": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@overpod/mcp-telegram"
],
"env": {
"TELEGRAM_API_ID": "your-value",
"TELEGRAM_API_HASH": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://mcp.mcp-telegram.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
服务器要求先登录,才会列出它的工具。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 mcp-telegram 验证,该账户拥有此仓库
代码最后更新于4天前
使用 MIT
在 129 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:TELEGRAM_API_ID, TELEGRAM_API_HASH
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于4天前,最新版本(1.45.1)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Vexa, emailmd, MCP WhatsApp Cloud
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
[📖 Documentation](https://mcp-telegram.github.io/mcp-telegram/) · [☁️ Cloud version](https://mcp-telegram.com) — connect Telegram to Claude.ai or ChatGPT in 30 seconds with QR code, no API keys needed.
Telegram MCP Server — a Model Context Protocol server that connects AI assistants like Claude and ChatGPT to Telegram via the MTProto protocol. Unlike bots, this runs as a userbot -- it operates under your personal Telegram account using GramJS, giving full access to your chats, contacts, and message history.
{pts, qts, date} stateMCP_TELEGRAM_ENABLE_STARS=1, v1.34.0)API_ID and API_HASH from my.telegram.orgTELEGRAM_API_ID=YOUR_ID TELEGRAM_API_HASH=YOUR_HASH npx @overpod/mcp-telegram login
A QR code will appear in the terminal. Open Telegram on your phone, go to Settings > Devices > Link Desktop Device, and scan the code. The session is saved to ~/.mcp-telegram/session and reused automatically.
Custom session path: set
TELEGRAM_SESSION_PATH=/path/to/sessionto store the session file elsewhere.
Two-step verification (2FA): if your account has a cloud password enabled, scanning the QR code is not enough — Telegram also requires the password. Provide it via
TELEGRAM_2FA_PASSWORDso the login can complete:
`bash
TELEGRAM_API_ID=YOUR_ID TELEGRAM_API_HASH=YOUR_HASH TELEGRAM_2FA_PASSWORD=YOUR_PASSWORD npx @overpod/mcp-telegram login
`
The password is only used locally to answer Telegram's SRP challenge and is never persisted.
Local files: tools that upload a file (
telegram-send-file,telegram-send-voice,telegram-send-album, stories, profile and group photos) read files under your home folder and temp folders, and downloads are saved toDownloads,Desktop,Documentsor temp folders. Hidden files and folders (~/.ssh,~/.mcp-telegram, ...),~/Library,~/AppDataand the session file are always refused, and an existing file is never overwritten (name (1).extis used). To use other folders, list them inMCP_TELEGRAM_FILE_DIRS(separated by:, or;on Windows); this replaces the defaults.
claude mcp add telegram -s user \
-e TELEGRAM_API_ID=YOUR_ID \ -e TELEGRAM_API_HASH=YOUR_HASH \ -- npx @overpod/mcp-telegram
That's it! Ask Claude to run telegram-status to verify.
Use TELEGRAM_SESSION_PATH to run separate Telegram accounts side by side:
# Login each account with a unique session path
TELEGRAM_API_ID=ID1 TELEGRAM_API_HASH=HASH1 TELEGRAM_SESSION_PATH=~/.mcp-telegram/session-work npx @overpod/mcp-telegram login TELEGRAM_API_ID=ID2 TELEGRAM_API_HASH=HASH2 TELEGRAM_SESSION_PATH=~/.mcp-telegram/session-personal npx @overpod/mcp-telegram login
Then add each as a separate MCP server:
claude mcp add telegram-work -s user \
-e TELEGRAM_API_ID=ID1 \ -e TELEGRAM_API_HASH=HASH1 \ -e TELEGRAM_SESSION_PATH=~/.mcp-telegram/session-work \ -- npx @overpod/mcp-telegram
claude mcp add telegram-personal -s user \ -e TELEGRAM_API_ID=ID2 \ -e TELEGRAM_API_HASH=HASH2 \ -e TELEGRAM_SESSION_PATH=~/.mcp-telegram/session-personal \ -- npx @overpod/mcp-telegram
Each account gets its own session file — no conflicts.
The opposite of multiple accounts: one account driven by many clients at once — several Claude Code windows, parallel sub-agents, or multiple IDEs. Normally each process opens the same session and they evict one another with AUTH_KEY_DUPLICATED. Serve mode fixes this.
Run a single persistent daemon that owns the one Telegram connection. Every other process auto-detects the daemon (via a PID lock) and becomes a thin client that proxies tool calls to it over a local Unix socket:
# On the host, once: start the daemon (owns the connection, no stdio)
TELEGRAM_API_ID=YOUR_ID TELEGRAM_API_HASH=YOUR_HASH mcp-telegram serve
serve argument)
Then point each MCP client at the same install with the same TELEGRAM_SESSION_PATH — no serve argument. They connect to the daemon automatically; closing any client never drops the shared connection. Credentials are only required by the daemon (the owner), so client commands can omit TELEGRAM_API_ID/TELEGRAM_API_HASH and keep them where the daemon runs.
See the [shared daemon guide](docs/guides/shared-daemon.md) for a systemd unit and SSH usage.
If Telegram is blocked or you're running in a containerized environment (Docker, K3s), use a SOCKS5 or MTProxy:
# SOCKS5 proxy
TELEGRAM_PROXY_IP=127.0.0.1 \ TELEGRAM_PROXY_PORT=10808 \ npx @overpod/mcp-telegram
TELEGRAM_PROXY_IP=proxy.example.com \ TELEGRAM_PROXY_PORT=443 \ TELEGRAM_PROXY_SECRET=ee00000000000000000000000000000000 \ npx @overpod/mcp-telegram
| Variable | Description |
|---|---|
TELEGRAM_PROXY_IP | Proxy server address |
TELEGRAM_PROXY_PORT | Proxy server port |
TELEGRAM_PROXY_SOCKS_TYPE | 4 or 5 (default: 5) |
TELEGRAM_PROXY_SECRET | MTProxy secret (enables MTProxy mode) |
TELEGRAM_PROXY_USERNAME | Optional proxy auth |
TELEGRAM_PROXY_PASSWORD | Optional proxy auth |
If your VPS or hosting IP is reachable on outbound port 443 but not the default MTProto port 80 (some cloud providers ban port 80 on Telegram DC IP ranges as anti-abuse policy), set:
TELEGRAM_USE_WSS=true npx @overpod/mcp-telegram
| Variable | Description |
|---|---|
TELEGRAM_USE_WSS | When true, gramJS uses port 443 instead of 80 for the MTProto TCPFull transport. Default: false. Cannot be combined with TELEGRAM_PROXY_* (gramJS limitation) — if both are set, useWSS is ignored and the proxy takes precedence (a warning is logged). |
No need to clone or install anything. Just use npx @overpod/mcp-telegram.
npm install -g @overpod/mcp-telegram
mcp-telegram # run server mcp-telegram login # QR login
Download from Releases — standalone single-file binaries, zero dependencies:
| Platform | Server | Login CLI |
|---|---|---|
| Linux x64 | mcp-telegram-linux-x64 | mcp-telegram-login-linux-x64 |
| Linux ARM64 | mcp-telegram-linux-arm64 | mcp-telegram-login-linux-arm64 |
| macOS x64 | mcp-telegram-darwin-x64 | mcp-telegram-login-darwin-x64 |
| macOS ARM64 | mcp-telegram-darwin-arm64 | mcp-telegram-login-darwin-arm64 |
| Windows x64 | mcp-telegram-windows-x64.exe | mcp-telegram-login-windows-x64.exe |
# Download (example for Linux x64)
curl -L -o mcp-telegram https://github.com/mcp-telegram/mcp-telegram/releases/latest/download/mcp-telegram-linux-x64 curl -L -o mcp-telegram-login https://github.com/mcp-telegram/mcp-telegram/releases/latest/download/mcp-telegram-login-linux-x64 chmod +x mcp-telegram mcp-telegram-login
TELEGRAM_API_ID=YOUR_ID TELEGRAM_API_HASH=YOUR_HASH ./mcp-telegram-login
./mcp-telegram
git clone https://github.com/mcp-telegram/mcp-telegram.git
cd mcp-telegram npm install && npm run build
docker build -t mcp-telegram https://github.com/mcp-telegram/mcp-telegram.git
Login (interactive terminal required):
docker run -it --rm \
-e TELEGRAM_API_ID=YOUR_ID \ -e TELEGRAM_API_HASH=YOUR_HASH \ -v ~/.mcp-telegram:/root/.mcp-telegram \ --entrypoint node mcp-telegram dist/qr-login-cli.js
Run the MCP server:
docker run -i --rm \
-e TELEGRAM_API_ID=YOUR_ID \ -e TELEGRAM_API_HASH=YOUR_HASH \ -v ~/.mcp-telegram:/root/.mcp-telegram \ mcp-telegram
Note: Login must be done once via terminal. After that, the session is persisted in
~/.mcp-telegramand reused a