Telegram
About
Bridges AI with Telegram to enable monitoring, organizing, and responding to messages through account access, dialog management, and conversation handling capabilities
Details
- Author
- chaindead
- Repository
- chaindead/telegram-mcp
- GitHub stars
- 30
- Downloads
- 180
- License
- MIT License
- Categories
- Communication, Other, Productivity, Developer Tools, AI, Infrastructure, API, Knowledge Base
- Tags
- #integration
Jump to
- [x] Get current account information (tool: tg_me)
- [x] List dialogs with optional unread filter (tool: tg_dialogs)
- [x] Mark dialog as read (tool: tg_read)
- [x] Retrieve messages from specific dialog (tool: tg_dialog)
- [x] Send draft messages to any dialog (tool: tg_send)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TelegramCommand (node, npx, python, etc.)telegram-mcpEnvironment-
HOME
<path_to_your_home_directory -
PATH
<path_to_telegram-mcp_binary_dir> -
TG_APP_ID
<your-app-id> -
TG_API_HASH
<your-api-hash>
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
HOME
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
brew install chaindead/tap/telegram-mcp
tg_me
Get current account information.
tg_dialogs
List dialogs with an optional unread filter.
tg_read
Mark a dialog as read.
tg_dialog
Retrieve messages from a specific dialog.
tg_send
Send draft messages to any dialog.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"telegram": {
"env": {
"HOME": "<path_to_your_home_directory",
"PATH": "<path_to_telegram-mcp_binary_dir>",
"TG_APP_ID": "<your-app-id>",
"TG_API_HASH": "<your-api-hash>"
},
"args": [],
"command": "telegram-mcp"
}
}
}
Linux
{
"env": {
"TG_APP_ID": "<your-app-id>",
"TG_API_HASH": "<your-api-hash>"
},
"args": [],
"command": "telegram-mcp"
}
Macos
{
"env": {
"HOME": "<path_to_your_home_directory",
"PATH": "<path_to_telegram-mcp_binary_dir>",
"TG_APP_ID": "<your-app-id>",
"TG_API_HASH": "<your-api-hash>"
},
"args": [],
"command": "telegram-mcp"
}
Windows
{
"env": {
"TG_APP_ID": "<your-app-id>",
"TG_API_HASH": "<your-api-hash>"
},
"args": [],
"command": "telegram-mcp"
}
The server is a bridge between the Telegram API and the AI assistants and is based on theModel Context Protocol.
[!IMPORTANT] Ensure that you have read and understood theTelegram API Terms of Servicebefore using this server. Any misuse of the Telegram API may result in the suspension of your account.
- What is MCP?
- What does this server do?
- Capabilities
- Prompt examples
- Message Management
- Organization
- Communication
- Homebrew
- NPX
- From Releases
- Authorization
- Client Configuration
- JSON Schema Version
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.
- 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)
Here are some example prompts you can use with AI assistants:
- "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"
- "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"
- "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"
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
You can run the latest version directly using npx (supports macOS, Linux, and Windows):
When using NPX, modify the standard commands and configuration as follows:
- Claude MCP server configurationbecomes:
{ "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, seeAuthorizationandClient Configuration.
Note:The commands below install to/usr/local/bin. To install elsewhere, replace/usr/local/binwith 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
# 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
Note:The commands below install to/usr/local/bin. To install elsewhere, replace/usr/local/binwith 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
# 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
- Download the latest release for your architecture:
go install github.com/chaindead/telegram-mcp@latest
Before you can use the server, you need to connect to the Telegram API.
-
Get the API ID and hash fromTelegram API
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.
Done! Please give this project a ⭐️ to support its development.
Example of Configuring Claude Desktop to recognize the Telegram 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
{ "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" } } } }
{ "mcpServers": { "telegram-mcp": { "command": "telegram-mcp", "env": { "TG_APP_ID": "<your-app-id>", "TG_API_HASH": "<your-api-hash>" } } } }
Some MCP clients (e.g. VS Code) do not support JSON Schema Draft 2020-12 and will reject tools that use it. You can override the JSON Schema version by setting the--schema-versionflag or theTG_SCHEMA_VERSIONenvironment variable.
Send and receive emails, SMS, and voice calls via Pingram.
Platfone - Receive SMS & Virtual Numbers MCP
Virtual phone number platform for AI agents — rent numbers across 200+ countries, receive SMS, and manage the full activation lifecycle
MCP server for Telegram bots built with aiogram. 30 tools, 7 resources, 3 prompts — messaging, rich media, moderation, interactive keyboards, real-time event streaming, rate limiting, permissions, and audit logging.
Production-grade MCP server for Telegram with dual-mode Bot API + MTProto, 6 composite tools
Local-first MCP server that puts your own LINE and Telegram chats behind one data layer — a daemon on your machine logs in with your own account, stores messages to JSONL + SQLite/FTS5, and exposes them to MCP clients like Claude Code. Not an npx one-liner: you clone the repo and run the daemon yourself.
Interact with the Didlogic API for telecommunication services, including virtual phone numbers and SMS.
Remote MCP server for managing WhatsApp and Telegram AI assistants: projects, prompts, conversations, leads and analytics, with no destructive tools by design.
Build, edit, and deploy Telegram bots on FlowCastle's hosted visual flow platform.
Read-only public stats for Telegram groups tracked by Limzo — activity, engagement, mood and leaderboards, no API key required.
Create AI-generated memes and convert them into stickers for Telegram and WhatsApp.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





