What are the prerequisites?
You need a Telegram API ID, API hash, and a phone number. These are set in a `.env` file alongside an optional `PORT` variable (defaults to 3000).
Telegram Client Library and MCP Server
@MCP-Mirror
Basic information
About Telegram Client Library and MCP Server
Mirror of
Telegram Client Library and MCP Server config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTelegram Client Library and MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Telegram Client Library and MCP Server?
This project provides both a Telegram client library and an MCP (Model Context Protocol) server for AI assistants to interact with Telegram. It’s for developers who want to build AI-powered tools that can read, search, and manage Telegram channels and messages.
How to use Telegram Client Library and MCP Server?
Set up a .env file with your Telegram API credentials, then run npm install to install dependencies. Start the MCP server with npm start (defaults to port 3000) and connect any MCP‑compatible assistant (e.g., Claude) to the server endpoint. You can also use the standalone client library directly in Node.js scripts.
Key features of Telegram Client Library and MCP Server
- Telegram authentication with 2FA support
- Automatic session reuse and management
- Retrieve chats/dialogs and fetch messages
- Filter messages using regex patterns
- Search Telegram channels by keywords
- List all accessible channels via MCP tools
Use cases of Telegram Client Library and MCP Server
- Have an AI assistant search Telegram channels and retrieve messages on demand
- Build automated monitoring or alerting workflows based on channel content
- Develop custom scripts that interact with Telegram using the client library
- Enable language models to read and analyze Telegram data through a standard MCP interface
Frequently asked questions
How does authentication work?
The library handles login (including 2FA) and automatically reuses saved sessions so you don’t need to re‑authenticate each time.
Where is session data stored?
Session files are saved to `./data/session.json` by default. You can override this path in the `TelegramClient` constructor.
Can I use it with AI assistants like Claude?
Yes. The MCP server exposes tools that any MCP‑compatible assistant can call to search channels, list channels, get messages, and filter by pattern.
What transport protocol does the MCP server use?
The server uses an HTTP/SSE transport layer, listening for connections on the configured port.
More Communication MCP servers
Mektup-mcp
WeeCiMektup gives AI agents and their humans a real email mailbox, not just a one-way sending API. Through 41 MCP tools, an agent can register a domain, create a mailbox, send and receive mail, and manage threads, drafts, fol
LinkedIn MCP Server: DMs, Inbox & Network for Claude, ChatGPT, Cursor
TalkToHumansLinkedIn MCP server for Claude, ChatGPT, Cursor & Codex. Read LinkedIn DMs, search your network, enrich profiles and draft messages you review before sending.
ARVX
Centric AI, Inc.Email for long-term client relationships: ARVX reads each person first and remembers every pair.
Caulo
PatryCaulo is the social layer of the agentic web: a social network your AI agent reads, briefs you on, and posts to — by prompt. Ad-free, verified humans only, with provenance on every post (human / agent-assisted / agent-au
AgentCouch
Messaging rooms for AI agents: hand off context across tools, worktrees, machines, and teammates. Agents meet in shared rooms over MCP, hand off directly, and leave a replayable transcript; live sessions wake on reply, b
Comments