Telegram MCP Server

What does “Telegram” MCP Server do?

The Telegram MCP Server integrates the powerful capabilities of the Telegram messaging platform with the Model Context Protocol (MCP), enabling AI assistants and clients to interact programmatically with Telegram. By utilizing the Telethon library, this server allows for comprehensive automation and management of chats, messages, groups, and user interactions within Telegram. It acts as a bridge between AI agents and Telegram’s API, making it possible to perform tasks such as sending messages, retrieving chat histories, managing groups, and more. This dramatically enhances development workflows by streamlining communication, facilitating automated responses, and providing tools to query or modify Telegram data directly from AI-powered tools like Claude, Cursor, and other MCP-compatible clients.

List of Prompts

No prompt templates were listed in the available documentation or repository files.

List of Resources

No explicit MCP resource primitives were documented or listed in the available files or README.

List of Tools

• get_chats(page, page_size): Returns a paginated list of Telegram chats and groups available to the authenticated user. This enables clients and LLMs to enumerate and select from the user’s conversation history for further analysis or messaging.

Documentation states that “Every major Telegram/Telethon feature is available as a tool,” but only get_chats is explicitly mentioned. The full list of tools is not provided in the visible documentation.

Use Cases of this MCP Server

• Automated Messaging: AI agents can send messages, media, or files to individuals or groups on Telegram, enabling automated notifications, responses, or broadcasts.
• Chat Analysis: Retrieve and analyze chat histories to summarize discussions, extract action items, or perform sentiment analysis within Telegram groups or private conversations.
• Group Management: Programmatically manage group membership, roles, and permissions for streamlined community or team administration.
• Bot Integration: Use the server to operate Telegram bots that perform complex workflows, relay information, or serve as AI-powered virtual assistants.
• Seamless Data Retrieval: Extract specific messages, files, or chat details for integration with external systems, dashboards, or databases, supporting advanced automation.

How to set it up

Windsurf

1. Prerequisite: Ensure Node.js is installed and Windsurf is configured.
2. Locate Configuration: Open your Windsurf settings or configuration file.
3. Add MCP Server: Insert the Telegram MCP server to the mcpServers section:

   {
     "mcpServers": {
       "telegram-mcp": {
         "command": "telegram-mcp",
         "args": ["serve"]
       }
     }
   }
   

4. Save and Restart: Save your configuration and restart Windsurf.
5. Verify Setup: Check the Windsurf dashboard or logs to ensure telegram-mcp is running.

Securing API Keys (example)

{
  "mcpServers": {
    "telegram-mcp": {
      "command": "telegram-mcp",
      "args": ["serve"],
      "env": {
        "TELEGRAM_API_ID": "<your_api_id>",
        "TELEGRAM_API_HASH": "<your_api_hash>",
        "TELEGRAM_SESSION_STRING": "<your_session_string>"
      }
    }
  }
}

Claude

1. Prerequisite: Ensure Claude Desktop or Claude-compatible client is installed.
2. Locate Configuration: Edit the claude_desktop_config.json file.
3. Add MCP Server Entry:

   {
     "mcpServers": {
       "telegram-mcp": {
         "command": "telegram-mcp",
         "args": ["serve"]
       }
     }
   }
   

4. Save and Restart: Save the JSON file and restart Claude.
5. Verify: Confirm that Claude detects and connects to telegram-mcp.

Securing API Keys (example)

{
  "mcpServers": {
    "telegram-mcp": {
      "command": "telegram-mcp",
      "args": ["serve"],
      "env": {
        "TELEGRAM_API_ID": "<your_api_id>",
        "TELEGRAM_API_HASH": "<your_api_hash>",
        "TELEGRAM_SESSION_STRING": "<your_session_string>"
      }
    }
  }
}

Cursor

1. Prerequisite: Install Node.js and Cursor editor.
2. Open Cursor Settings: Access the MCP integration section.
3. Add Telegram MCP Server:

   {
     "mcpServers": {
       "telegram-mcp": {
         "command": "telegram-mcp",
         "args": ["serve"]
       }
     }
   }
   

4. Restart Cursor: Save settings and restart the Cursor app.
5. Verify: Confirm Cursor recognizes and connects to the Telegram MCP server.

Securing API Keys (example)

{
  "mcpServers": {
    "telegram-mcp": {
      "command": "telegram-mcp",
      "args": ["serve"],
      "env": {
        "TELEGRAM_API_ID": "<your_api_id>",
        "TELEGRAM_API_HASH": "<your_api_hash>",
        "TELEGRAM_SESSION_STRING": "<your_session_string>"
      }
    }
  }
}

Cline

1. Prerequisite: Ensure Cline is installed and configured.
2. Open Configuration File: Edit your Cline settings or config file.
3. Insert MCP Server Entry:

   {
     "mcpServers": {
       "telegram-mcp": {
         "command": "telegram-mcp",
         "args": ["serve"]
       }
     }
   }
   

4. Save & Restart: Save the file, restart Cline.
5. Verify: Check Cline interface for the running Telegram MCP server.

Securing API Keys (example)

{
  "mcpServers": {
    "telegram-mcp": {
      "command": "telegram-mcp",
      "args": ["serve"],
      "env": {
        "TELEGRAM_API_ID": "<your_api_id>",
        "TELEGRAM_API_HASH": "<your_api_hash>",
        "TELEGRAM_SESSION_STRING": "<your_session_string>"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "telegram-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “telegram-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: No explicit mention
Sampling support: No explicit mention

I would rate the Telegram MCP Server a 6/10. It is functionally robust with clear setup and security instructions, but lacks documentation on prompt templates, explicit resources, and an exhaustive tool list, which are important for advanced MCP integration and transparency.

MCP Score