telegram-mcp-kit
Exposes the Telegram Bot API as tools for Claude Code or any MCP client, enabling message sending, chat management, file handling, and bot information retrieval.
README
🚀 telegram-mcp-kit
MCP server that exposes the Telegram Bot API as tools for Claude Code (or any MCP client).
Table of Contents
- 🚀 Quick Start
- 🛠️ Installation
- 📦 Features
- 🤝 How to Contribute
- 💬 Community & Support
- 👥 Repo Contributors
- ⚖️ License
- 🌟 Star History
🚀 Quick Start
Get your bot token from @BotFather on Telegram. Once the server is configured, you can run /mcp inside Claude Code to verify it is connected.
🛠️ Installation
Get your bot token from @BotFather on Telegram first.
Option 1: From PyPI (recommended)
claude mcp add telegram-mcp-kit \
-e TELEGRAM_BOT_TOKEN=your-bot-token-here \
-e TELEGRAM_CHAT_ID=your-chat-id \
-- uvx telegram-mcp-kit
<details> <summary>Manual MCP config</summary>
{
"mcpServers": {
"telegram-mcp-kit": {
"command": "uvx",
"args": ["telegram-mcp-kit"],
"env": {
"TELEGRAM_BOT_TOKEN": "your-bot-token-here",
"TELEGRAM_CHAT_ID": "your-chat-id"
}
}
}
}
</details>
Option 2: From GitHub
claude mcp add telegram-mcp-kit \
-e TELEGRAM_BOT_TOKEN=your-bot-token-here \
-e TELEGRAM_CHAT_ID=your-chat-id \
-- uvx --from "git+https://github.com/QuocTang/telegram-mcp-kit.git" telegram-mcp-kit
<details> <summary>Manual MCP config</summary>
{
"mcpServers": {
"telegram-mcp-kit": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/QuocTang/telegram-mcp-kit.git",
"telegram-mcp-kit"
],
"env": {
"TELEGRAM_BOT_TOKEN": "your-bot-token-here",
"TELEGRAM_CHAT_ID": "your-chat-id"
}
}
}
}
</details>
Option 3: From source
git clone https://github.com/QuocTang/telegram-mcp-kit.git
cd telegram-mcp-kit
cp .env.example .env # add your TELEGRAM_BOT_TOKEN
uv sync
claude mcp add telegram-mcp-kit \
-- uv run --directory /absolute/path/to/telegram-mcp-kit telegram-mcp-kit
<details> <summary>Manual MCP config</summary>
{
"mcpServers": {
"telegram-mcp-kit": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/telegram-mcp-kit",
"telegram-mcp-kit"
]
}
}
}
With this option,
TELEGRAM_BOT_TOKENis read from the.envfile inside the project directory.
</details>
Environment variables
| Variable | Required | Description |
|---|---|---|
TELEGRAM_BOT_TOKEN |
Yes | Token from BotFather |
TELEGRAM_CHAT_ID |
No | Default chat ID (if set, chat_id can be omitted in tool calls) |
MCP_TRANSPORT |
No | stdio (default) or sse |
MCP_HOST |
No | Bind host (default 127.0.0.1) |
MCP_PORT |
No | Bind port (default 8000) |
HTTP_TIMEOUT |
No | Telegram API timeout in seconds (default 30) |
📦 Features
| 🚀 Feature | 📝 Description |
|---|---|
| 🛠️ 20+ Tools | Comprehensive coverage for messages, chat management, files/photos, and bot info. |
| 🔍 Auto-discovery | Simply add a Python file to the tools/ folder and it registers automatically. |
| 📡 Flexible Transport | Works seamlessly over stdio (for local clients) or SSE (remote/Docker). |
Tools List
Messages
| Tool | Description |
|---|---|
send_message |
Send a text message (Markdown/HTML) |
edit_message |
Edit an existing message |
delete_message |
Delete a message |
forward_message |
Forward a message between chats |
Updates
| Tool | Description |
|---|---|
get_updates |
Fetch recent messages/updates the bot received |
Chat management
| Tool | Description |
|---|---|
get_chat_info |
Get chat metadata (name, type, description) |
get_chat_member_count |
Count members |
get_chat_admins |
List administrators |
ban_member |
Ban a user |
unban_member |
Unban a user |
set_chat_title |
Change group/channel title |
set_chat_description |
Change group/channel description |
pin_message |
Pin a message |
unpin_message |
Unpin a message |
Files & photos
| Tool | Description |
|---|---|
send_photo |
Send a photo by URL or file_id |
send_photo_file |
Send a local photo file |
send_document |
Send a document by URL or file_id |
send_document_file |
Send a local file as document |
get_file_info |
Get file metadata + download link |
Bot
| Tool | Description |
|---|---|
get_bot_info |
Get bot name, username, etc. |
🤝 How to Contribute
We welcome contributions! Please follow these steps:
- Fork the repository.
- Create a new branch for your feature.
- Submit a Pull Request.
See CONTRIBUTING.md for how to add new tools.
Development
uv sync # install all deps (including dev)
uv run pytest -v # run tests
uv run ruff check src/ tests/ # lint
💬 Community & Support
If this repository saves you time, please star the repository!
👥 Repo Contributors
<a href="https://github.com/QuocTang/telegram-mcp-kit/graphs/contributors"> <img src="https://contrib.rocks/image?repo=QuocTang/telegram-mcp-kit" alt="Repository contributors" /> </a>
Made with contrib.rocks.
⚖️ License
MIT License. See LICENSE for details.
🌟 Star History
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.