Telegram MCP Server
An MCP server implementation that provides tools for interacting with the [Telegram Bot API](
NexusX-MCP
README
Telegram MCP Server
An MCP server implementation that provides tools for interacting with the Telegram Bot API. This service allows AI assistants to send messages and retrieve bot information programmatically.
Tools
The Telegram MCP Service provides the following tools for interacting with the Telegram Bot API:
get_bot_info
Retrieves basic information about the bot.
- No parameters required
- Returns a User object containing bot information
send_message
Sends a message to a specified chat.
chatId
: Unique identifier for the target chat (can be string or number)text
: Text of the message to be sentparams
(optional): Additional parameters for the message (e.g., parse_mode, reply_markup, etc.)
get_updates
Receives incoming updates using long polling.
params
(optional): Object containing optional parameters:offset
(optional): Identifier of the first update to be returnedlimit
(optional): Limits the number of updates to be retrieved (1-100)timeout
(optional): Timeout in seconds for long pollingallowed_updates
(optional): Array of update types to receive
- Returns an array of Update objects containing various types of updates:
- Messages and edited messages
- Channel posts
- Business messages
- Inline queries
- Callback queries
- Shipping queries
- Pre-checkout queries
- Polls and poll answers
- Chat member updates
- Chat join requests
- Chat boosts
forward_message
Forwards messages of any kind. Service messages and messages with protected content can't be forwarded.
chatId
: Unique identifier for the target chat or username of the target channel (in the format @channelusername)fromChatId
: Unique identifier for the chat where the original message was sent (or channel username in the format @channelusername)messageId
: Message identifier in the chat specified in from_chat_idparams
(optional): Object containing optional parameters:message_thread_id
(optional): Unique identifier for the target message thread (topic) of the forum; for forum supergroups onlyvideo_start_timestamp
(optional): New start timestamp for the forwarded video in the messagedisable_notification
(optional): Sends the message silently. Users will receive a notification with no sound.protect_content
(optional): Protects the contents of the forwarded message from forwarding and saving
- Returns the sent Message object on success
Configuration
Environment Variables
You need to set up the following environment variable:
TELEGRAM_BOT_TOKEN=your_bot_token
You can get your bot token by talking to @BotFather on Telegram and creating a new bot.
Creating a new bot
Use the /newbot
command to create a new bot. @BotFather
will ask you for a name and username, then generate an authentication token for your new bot.
The name of your bot is displayed in contact details and elsewhere.
The username is a short name, used in search, mentions and t.me links. Usernames are 5-32 characters long and not case sensitive – but may only include Latin characters, numbers, and underscores. Your bot's username must end in 'bot', like 'tetris_bot' or 'TetrisBot'.
The token is a string, like 110201543:AAHdqTcvCH1vGWJxfSeofSAs0K5PALDsaw, which is required to authorize the bot and send requests to the Bot API. Keep your token secure and store it safely, it can be used by anyone to control your bot.
Unlike the bot's name, the username cannot be changed later – so choose it carefully. When sending a request to api.telegram.org, remember to prefix the word 'bot' to your token.
Development
npm install
npm run build
npx @modelcontextprotocol/inspector node dist/index.js
Open http://127.0.0.1:6274 to set up the environment and interact with the tools.
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.