Telegram MCP Server — connect Telegram to Claude AI & ChatGPT. 181 tools: messages, media, reactions, polls, stories & more. MTProto userbot. Self-host (npx) or hosted at mcp-telegram.com.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp-telegram -- npx -y @overpod/mcp-telegram{
"mcpServers": {
"mcp-telegram": {
"command": "npx",
"args": ["-y", "@overpod/mcp-telegram"],
"env": {
"TELEGRAM_2FA_PASSWORD": "<telegram_2fa_password>",
"TELEGRAM_PROXY_SECRET": "<telegram_proxy_secret>"
}
}
}
}TELEGRAM_2FA_PASSWORDTELEGRAM_PROXY_SECRETResumen de MCP Servers
# Telegram MCP Server
[](https://www.npmjs.com/package/@overpod/mcp-telegram)
[](https://www.npmjs.com/package/@overpod/mcp-telegram)
[](https://nodejs.org/)
[](https://www.typescriptlang.org/)
[](https://modelcontextprotocol.io/)
[](LICENSE)
[](https://glama.ai/mcp/servers/overpod/mcp-telegram)
> **[📖 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.
<p align="center">
<img src="assets/demo.gif" alt="MCP Telegram demo — connect and summarize chats in Claude" width="700">
</p>
**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](https://github.com/nicedoc/gramjs), giving full access to your chats, contacts, and message history.
## Features
- **Comprehensive tool coverage** -- the most full-featured Telegram MCP server available
- **MTProto protocol** -- direct Telegram API access, not the limited Bot API
- **Userbot** -- operates as your personal account, not a bot
- **Full-featured** -- messaging, reactions, polls, scheduled messages, stickers, media, contacts, and more
- **Forum Topics** -- list topics, read per-topic messages, send to specific topics, per-topic unread counts
- **Stickers** -- search sticker sets, browse installed/recent stickers, send stickers to any chat
- **Account & profile management** -- update profile, set emoji status, birthday, personal channel, profile photo, manage privacy settings, sessions, auto-delete timers
- **Chat folders** -- create, edit, delete and reorder folders, toggle folder tags, read suggested folders (v1.33.0)
- **Global privacy** -- read and set account-wide privacy settings (v1.33.0)
- **Global search** -- search messages across all chats at once
- **Real-time polling** -- fetch updates via stateless cursors; agent owns `{pts, qts, date}` state
- **Inline bots & buttons** -- query inline bots, send results, press callback buttons
- **Stories** -- read stories from peers, get story view stats; publish/edit/delete stories, react, pin, stealth mode, archive, report (v1.30.0)
- **Discussion** -- get discussion-group info for channel posts with comments, list groups eligible for discussion (v1.30.0)
- **Read Receipts** -- who read a message in a small group, when your private message was read (v1.30.0)
- **Admin controls** -- toggle channel signatures, anti-spam, forum mode, prehistory; approve join requests
- **Stats** -- channel and supergroup analytics (GetBroadcastStats / GetMegagroupStats)
- **Boosts & Business** -- boost status, boosters list, Telegram Business chat links CRUD, work hours, location, greeting/away/intro messages
- **Star gifts** -- browse available and saved gifts, save/convert gifts, manage Stars balance and subscriptions (opt-in via `MCP_TELEGRAM_ENABLE_STARS=1`, v1.34.0)
- **Shared daemon** -- one background process serves multiple MCP clients over a single Telegram session; see the [shared-daemon guide](https://mcp-telegram.github.io/mcp-telegram/guides/shared-daemon) (v1.38.0)
- **QR code login** -- authenticate by scanning a QR code in the Telegram app
- **Session persistence** -- login once, stay connected across restarts
- **Human-readable output** -- sender names are resolved, not just numeric IDs
- **Works with any MCP client** -- Claude Code, Claude Desktop, ChatGPT, Cursor, VS Code, Mastra, etc.
## Prerequisites
- **Node.js** 18 or later
- **Telegram API credentials** -- `API_ID` and `API_HASH` from [my.telegram.org](https://my.telegram.org)
## Quick Start
### 1. Get Telegram API credentials
1. Go to [my.telegram.org](https://my.telegram.org) and log in with your phone number.
2. Navigate to **API development tools**.
3. Create a new application (any name and platform).
4. Copy the **App api_id** and **App api_hash**.
### 2. Login
```bash
TELEGRAM_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/session` to 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_PASSWORD` so 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.
### 3. Add to Claude
```bash
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.
### Multiple Accounts
Use `TELEGRAM_SESSION_PATH` to run separate Telegram accounts side by side:
```bash
# 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:
```bash
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.
### Multiple agents / concurrent clients (shared daemon)
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:
```bash
# 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
# (or set MCP_TELEGRAM_DAEMON=1 instead of the `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.
### Proxy Support
If Telegram is blocked or you're running in a containerized environment (Docker, K3s), use a SOCKS5 or MTProxy:
```bash
# SOCKS5 proxy
TELEGRAM_PROXY_IP=127.0.0.1 \
TELEGRAM_PROXY_PORT=10808 \
npx @overpod/mcp-telegram
# MTProxy
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 |
### Connecting via WSS (port 443)
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:
```bash
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). |
## Installation Options
### npx (recommended, zero install)
No need to clone or install anything. Just use `npx @overpod/mcp-telegram`.
### Global install
```bash
npm install -g @overpod/mcp-telegram
mcp-telegram # run server
mcp-telegram login # QR login
```
### Pre-built binary (no runtime needed)
Download from [Releases](https://github.com/mcp-telegram/mcp-telegram/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-dLo que la gente pregunta sobre mcp-telegram
¿Qué es mcp-telegram/mcp-telegram?
+
mcp-telegram/mcp-telegram es mcp servers para el ecosistema de Claude AI. Telegram MCP Server — connect Telegram to Claude AI & ChatGPT. 181 tools: messages, media, reactions, polls, stories & more. MTProto userbot. Self-host (npx) or hosted at mcp-telegram.com. Tiene 34 estrellas en GitHub y su última actualización registrada es del 2026-08-27.
¿Cómo se instala mcp-telegram?
+
Puedes instalar mcp-telegram clonando el repositorio (https://github.com/mcp-telegram/mcp-telegram) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar mcp-telegram/mcp-telegram?
+
Nuestro agente de seguridad ha analizado mcp-telegram/mcp-telegram y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene mcp-telegram/mcp-telegram?
+
mcp-telegram/mcp-telegram es mantenido por mcp-telegram. La última actividad registrada en GitHub es del 2026-08-27, con 2 issues abiertos.
¿Hay alternativas a mcp-telegram?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega mcp-telegram en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/mcp-telegram-mcp-telegram)<a href="https://claudewave.com/repo/mcp-telegram-mcp-telegram"><img src="https://claudewave.com/api/badge/mcp-telegram-mcp-telegram" alt="Featured on ClaudeWave: mcp-telegram/mcp-telegram" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!