
mcp-telegram
MCP server to work with Telegram through MTProto
1
Github Watches
7
Github Forks
67
Github Stars
Telegram MCP server
- Telegram MCP server
About
The server is a bridge between the Telegram API and the AI assistants and is based on the Model Context Protocol.
[!IMPORTANT] Ensure that you have read and understood the Telegram API Terms of Service before using this server. Any misuse of the Telegram API may result in the suspension of your account.
What is MCP?
The Model Context Protocol (MCP) is a system that lets AI apps, like Claude Desktop, connect to external tools and data sources. It gives a clear and safe way for AI assistants to work with local services and APIs while keeping the user in control.
What does this server do?
As of not, the server provides read-only access to the Telegram API.
- Get the list of dialogs (chats, channels, groups)
- Get the list of (unread) messages in the given dialog
- Mark chanel as read
- Retrieve messages by date and time
- Download media files
- Get the list of contacts
- Draft a message
- ...
Practical use cases
- Create a summary of the unread messages
- Find contacts with upcoming birthdays and schedule a greeting
- Find discussions on a given topic, summarize them and provide a list of links
Prerequisites
Installation
uv tool install git+https://github.com/sparfenyuk/mcp-telegram
[!NOTE] If you have already installed the server, you can update it using
uv tool upgrade --reinstall
command.
[!NOTE] If you want to delete the server, use the
uv tool uninstall mcp-telegram
command.
Configuration
Telegram API Configuration
Before you can use the server, you need to connect to the Telegram API.
-
Get the API ID and hash from Telegram API
-
Run the following command:
mcp-telegram sign-in --api-id <your-api-id> --api-hash <your-api-hash> --phone-number <your-phone-number>
Enter the code you received from Telegram to connect to the API.
The password may be required if you have two-factor authentication enabled.
[!NOTE] To log out from the Telegram API, use the
mcp-telegram logout
command.
Claude Desktop Configuration
Configure Claude Desktop to recognize the Exa MCP server.
-
Open the Claude Desktop configuration file:
- in MacOS, the configuration file is located at
~/Library/Application Support/Claude/claude_desktop_config.json
- in Windows, the configuration file is located at
%APPDATA%\Claude\claude_desktop_config.json
Note: You can also find claude_desktop_config.json inside the settings of Claude Desktop app
- in MacOS, the configuration file is located at
-
Add the server configuration
{ "mcpServers": { "mcp-telegram": { "command": "mcp-server", "env": { "TELEGRAM_API_ID": "<your-api-id>", "TELEGRAM_API_HASH": "<your-api-hash>", }, } } } }
Telegram Configuration
Before working with Telegram’s API, you need to get your own API ID and hash:
- Login to your Telegram account with the phone number of the developer account to use.
- Click under API Development tools.
- A 'Create new application' window will appear. Fill in your application details. There is no need to enter any URL, and only the first two fields (App title and Short name) can currently be changed later.
- Click on 'Create application' at the end. Remember that your API hash is secret and Telegram won’t let you revoke it. Don’t post it anywhere!
Development
Getting started
-
Clone the repository
-
Install the dependencies
uv sync
-
Run the server
uv run mcp-telegram --help
Tools can be added to the src/mcp_telegram/tools.py
file.
How to add a new tool:
-
Create a new class that inherits from ToolArgs
class NewTool(ToolArgs): """Description of the new tool.""" pass
Attributes of the class will be used as arguments for the tool. The class docstring will be used as the tool description.
-
Implement the tool_runner function for the new class
@tool_runner.register async def new_tool(args: NewTool) -> t.Sequence[TextContent | ImageContent | EmbeddedResource]: pass
The function should return a sequence of TextContent, ImageContent or EmbeddedResource. The function should be async and accept a single argument of the new class.
-
Done! Restart the client and the new tool should be available.
Validation can accomplished either through Claude Desktop or by running the tool directly.
Debugging the server in terminal
To run the tool directly, use the following command:
# List all available tools
uv run cli.py list-tools
# Run the concrete tool
uv run cli.py call-tool --name ListDialogs --arguments '{"unread": true}'
Debugging the server in the Inspector
The MCP inspector is a tool that helps to debug the server using fancy UI. To run it, use the following command:
npx @modelcontextprotocol/inspector uv run mcp-telegram
[!WARNING] Do not forget to define Environment Variables TELEGRAM_API_ID and TELEGRAM_API_HASH in the inspector.
Troubleshooting
Message 'Could not connect to MCP server mcp-telegram'
If you see the message 'Could not connect to MCP server mcp-telegram' in Claude Desktop, it means that the server configuration is incorrect.
Try the following:
- Use the full path to the
uv
binary in the configuration file - Check the path to the cloned repository in the configuration file
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Take an adjectivised noun, and create images making it progressively more adjective!
Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
🧑🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.
Reviews

user_PRKm5lTR
I have been using mcp-telegram by sparfenyuk for a while now, and it has exceeded my expectations. The seamless integration with Telegram makes managing my bots incredibly efficient. The setup was straightforward, and the welcome messages are engaging. Highly recommend checking it out on GitHub: https://github.com/sparfenyuk/mcp-telegram.