agent-telegram-mcp
Enables AI agents to send and receive messages, media, and files on Telegram, and manage chats via a bot token.
README
agent-telegram-mcp
A robust Model Context Protocol (MCP) server that enables AI agents to seamlessly interact with Telegram using a standard Bot Token. It provides a comprehensive suite of tools for bidirectional communication, including sending and receiving text messages, multimedia, documents, and managing chats.
Installation
Install using pip or uv:
pip install agent-telegram-mcp
or
uv tool install agent-telegram-mcp
Configuration
This MCP server requires a Telegram Bot Token. You can create a new bot and obtain your token by talking to the BotFather on Telegram.
To use this server with MCP-compatible clients (like Claude Desktop, Agent_head, etc.), add it to your server configuration and pass the token as an environment variable:
Example mcp_config.json
{
"mcpServers": {
"agent-telegram-mcp": {
"command": "agent-telegram-mcp",
"env": {
"TELEGRAM_BOT_TOKEN": "123456789:ABCdefGHIjklMNOpqrSTUvwxYZ"
}
}
}
}
Available Tools
The server exposes the following tools to the LLM agent:
✉️ Messaging
telegram_send_message: Send text messages (supports Markdown, HTML, silent messages, and replies).telegram_forward_message: Forward existing messages between chats.telegram_delete_message: Delete a message from a chat (requires bot admin permissions).telegram_pin_message: Pin a message in a group/channel.
🖼️ Media & Files
telegram_send_photo: Send images via a local file path, public HTTP URL, or Telegram file ID.telegram_send_video: Send video files.telegram_send_audio: Send audio tracks (renders as a Telegram music player).telegram_send_voice: Send voice notes (.oggfiles).telegram_send_document: Send arbitrary files (PDFs, ZIPs, code snippets, etc.).telegram_send_sticker: Send.webpstickers.telegram_send_location: Send a geographic map pin via latitude and longitude.
📥 Retrieval & Info
telegram_get_updates: Retrieve recent messages, commands, and callback queries sent to the bot (supports pagination withoffsetandlimit).telegram_get_chat_info: Fetch detailed information about a user, group, or channel.telegram_get_chat_member_count: Check how many users are in a chat.telegram_get_file_info: Retrieve metadata and the download path for a file hosted on Telegram servers.telegram_download_file: Download a file to a specific local path or return its contents as a Base64 string.telegram_get_bot_info: Fetch the current bot's profile information to verify the token connection.
Development & Testing
You can run the server directly via standard I/O (stdio) transport:
export TELEGRAM_BOT_TOKEN="your-token"
# On Windows: set TELEGRAM_BOT_TOKEN=your-token
agent-telegram-mcp
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.
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.
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.
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.