Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

telegram-mcp

MCP.Pizza Chef: chaindead

Telegram MCP is a server that acts as a bridge between the Telegram API and AI assistants, enabling management of dialogs, messages, drafts, and read statuses. It leverages the Model Context Protocol to provide structured, real-time context from Telegram to language models, facilitating seamless interaction and automation within Telegram conversations. This server is OS-agnostic and designed for integration with various AI workflows.

Use This MCP server To

Manage Telegram dialogs and message threads programmatically Track and update message read statuses in real time Handle message drafts and edits via AI-driven workflows Integrate Telegram conversations into AI assistant environments Automate responses and message handling using LLMs Bridge Telegram API data into multi-model AI applications

README

License: MIT Visitors

Telegram MCP server

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.

Table of Contents

What is MCP?

The Model Context Protocol (MCP) is a system that lets AI apps, like Claude Desktop or Cursor, 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?

Capabilities

  • Get current account information (tool: tg_me)
  • List dialogs with optional unread filter (tool: tg_dialogs)
  • Mark dialog as read (tool: tg_read)
  • Retrieve messages from specific dialog (tool: tg_dialog)
  • Send draft messages to any dialog (tool: tg_send)

Prompt examples

Here are some example prompts you can use with AI assistants:

Message Management

  • "Check for any unread important messages in my Telegram"
  • "Summarize all my unread Telegram messages"
  • "Read and analyze my unread messages, prepare draft responses where needed"
  • "Check non-critical unread messages and give me a brief overview"

Organization

  • "Analyze my Telegram dialogs and suggest a folder structure"
  • "Help me categorize my Telegram chats by importance"
  • "Find all work-related conversations and suggest how to organize them"

Communication

  • "Monitor specific chat for updates about [topic]"
  • "Draft a polite response to the last message in [chat]"
  • "Check if there are any unanswered questions in my chats"

Installation

Homebrew

You can install a binary release on macOS/Linux using brew:

# Install
brew install chaindead/tap/telegram-mcp

# Update
brew upgrade chaindead/tap/telegram-mcp

NPX

You can run the latest version directly using npx (supports macOS, Linux, and Windows):

npx -y @chaindead/telegram-mcp

When using NPX, modify the standard commands and configuration as follows:

npx -y @chaindead/telegram-mcp auth ...
{
  "mcpServers": {
    "telegram": {
      "command": "npx",
      "args": ["-y", "@chaindead/telegram-mcp"],
      "env": {
        "TG_APP_ID": "<your-api-id>",
        "TG_API_HASH": "<your-api-hash>"
      }
    }
  }
}

For complete setup instructions, see Authorization and Client Configuration.

From Releases

MacOS

Note: The commands below install to /usr/local/bin. To install elsewhere, replace /usr/local/bin with your preferred directory in your PATH.

First, download the archive for your architecture:

# For Intel Mac (x86_64)
curl -L -o telegram-mcp.tar.gz https://github.com/chaindead/telegram-mcp/releases/latest/download/telegram-mcp_Darwin_x86_64.tar.gz

# For Apple Silicon (M1/M2)
curl -L -o telegram-mcp.tar.gz https://github.com/chaindead/telegram-mcp/releases/latest/download/telegram-mcp_Darwin_arm64.tar.gz

Then install the binary:

# Extract the binary
sudo tar xzf telegram-mcp.tar.gz -C /usr/local/bin

# Make it executable
sudo chmod +x /usr/local/bin/telegram-mcp

# Clean up
rm telegram-mcp.tar.gz

Linux

Note: The commands below install to /usr/local/bin. To install elsewhere, replace /usr/local/bin with your preferred directory in your PATH.

First, download the archive for your architecture:

# For x86_64 (64-bit)
curl -L -o telegram-mcp.tar.gz https://github.com/chaindead/telegram-mcp/releases/latest/download/telegram-mcp_Linux_x86_64.tar.gz

# For ARM64
curl -L -o telegram-mcp.tar.gz https://github.com/chaindead/telegram-mcp/releases/latest/download/telegram-mcp_Linux_arm64.tar.gz

Then install the binary:

# Extract the binary
sudo tar xzf telegram-mcp.tar.gz -C /usr/local/bin

# Make it executable
sudo chmod +x /usr/local/bin/telegram-mcp

# Clean up
rm telegram-mcp.tar.gz

Windows

Windows

  1. Download the latest release for your architecture:
  2. Extract the .zip file
  3. Add the extracted directory to your PATH or move telegram-mcp.exe to a directory in your PATH

From Source

Requirements:

  • Go 1.24 or later
  • GOBIN in PATH
go install github.com/chaindead/telegram-mcp@latest

Configuration

Authorization

Before you can use the server, you need to connect to the Telegram API.

  1. Get the API ID and hash from Telegram API

  2. Run the following command:

    Note: If you have 2FA enabled: add --password <2fa_password>

    Note: If you want to override existing session: add --new

    telegram-mcp auth --app-id <your-api-id> --api-hash <your-api-hash> --phone <your-phone-number>

    📩 Enter the code you received from Telegram to connect to the API.

  3. Done! Please give this project a ⭐️ to support its development.

Client Configuration

Example of Configuring Claude Desktop to recognize the Telegram MCP server.

  1. 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

  2. Add the server configuration

    for Claude desktop:

     {
       "mcpServers": {
         "telegram": {
           "command": "telegram-mcp",
           "env": {
             "TG_APP_ID": "<your-app-id>",
             "TG_API_HASH": "<your-api-hash>",
             "PATH": "<path_to_telegram-mcp_binary_dir>",
             "HOME": "<path_to_your_home_directory"
           }
         }
       }
     }

    for Cursor:

    {
      "mcpServers": {
        "telegram-mcp": {
          "command": "telegram-mcp",
          "env": {
            "TG_APP_ID": "<your-app-id>",
            "TG_API_HASH": "<your-api-hash>"
          }
        }
      }
    }

Star History

Star History Chart

telegram-mcp FAQ

How do I install the telegram-mcp server?
Follow the installation instructions on the GitHub repository, ensuring you meet all dependencies and have a valid Telegram API key.
Is telegram-mcp server platform dependent?
No, telegram-mcp is OS-agnostic and works across different operating systems.
What permissions are required to use telegram-mcp?
You must comply with Telegram API Terms of Service and have appropriate API access tokens to manage messages and dialogs.
Can telegram-mcp handle real-time message updates?
Yes, it supports real-time tracking of message statuses including read receipts and new messages.
Does telegram-mcp support integration with multiple AI models?
Yes, it is designed to work with various LLM providers like OpenAI, Anthropic Claude, and Google Gemini.
How secure is the telegram-mcp server?
It follows best practices for secure API interaction and scoped access, but users should ensure secure deployment environments.
Can telegram-mcp manage message drafts?
Yes, it supports managing drafts, allowing AI assistants to read and modify draft messages.
Where can I find the source code and license information?
The source code is available on GitHub under the MIT license.