The server is a bridge between the Telegram API and the AI assistants and is based on the
Important
Ensure that you have read and understood the
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):
npx -y @chaindead/telegram-mcp
When using NPX, modify the standard commands and configuration as follows:
- Authentication command becomes:
npx -y @chaindead/telegram-mcp auth ...
- Claude MCP server configuration becomes:
{
"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.
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
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
- Download the latest release for your architecture:
- Extract the
.zip
file - Add the extracted directory to your PATH or move
telegram-mcp.exe
to a directory in your PATH
Requirements:
- Go 1.24 or later
- GOBIN in PATH
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 from
Telegram API -
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.
-
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
- in MacOS, the configuration file is located at
-
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>" } } } }