mcpField
T
Telegram MCP Server

Telegram MCP Server

Local
github.com/kfastovCommunication44Updated 1w ago
Repository

About Telegram MCP Server

tgcli is a Telegram command line tool with background sync and an optional MCP server, operating on a personal account via MTProto rather than the Bot API. It suits users who want to archive, search and send personal Telegram messages from the terminal or from an AI client.

Key features

  1. 01Command line message listing and search
  2. 02Background realtime sync and archive backfill
  3. 03Channel and message listing
  4. 04Machine-readable --json output
  5. 05Optional MCP server

Use cases

  1. 01Archiving and searching Telegram messages locally
  2. 02Sending text or files from the command line
  3. 03Letting an MCP client access personal Telegram data

MCP support

When enabled, tgcli server exposes an MCP endpoint at a local address (default http://127.0.0.1:8080/mcp) for MCP clients to connect to.

#telegram#mcp#telegram-client#ai-agents#mcp-server#fastmcp#client-library

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

tgcli

Telegram CLI with background sync and an optional MCP server for your personal account (MTProto, not bot API).

Installation

npm install -g @kfastov/tgcli

brew install kfastov/tap/tgcli

Authentication

Get Telegram API credentials:

  1. Go to https://my.telegram.org/apps
  2. Log in with your phone number
  3. Create a new application
  4. Copy api_id and api_hash

Then authenticate:

tgcli auth

Quick start

tgcli auth
tgcli sync --follow
tgcli messages list --chat @username --limit 20
tgcli messages search "course" --chat @channel --source archive
tgcli send text --to @username --message "hello"
tgcli server

Commands

tgcli auth           Authentication and session setup
tgcli config         View and edit config
tgcli sync           Archive backfill and realtime sync
tgcli server         Run background sync service (MCP optional)
tgcli service        Install/start/stop/status/logs for background service
tgcli channels       List/search channels
tgcli messages       List/search messages
tgcli send           Send text or files
tgcli media          Download media
tgcli topics         Forum topics
tgcli tags           Channel tags
tgcli metadata       Channel metadata cache
tgcli contacts       Contacts and people
tgcli groups         Group management
tgcli doctor         Diagnostics and sanity checks

Use tgcli [command] --help for details. Add --json for machine-readable output.

MCP (optional)

Enable it via config:

tgcli config set mcp.enabled true

By default the server binds to http://127.0.0.1:8080/mcp. To change it:

tgcli config set mcp.host 127.0.0.1
tgcli config set mcp.port 8080

Then run tgcli server and point your client at the configured address.

Configuration & Store

The tgcli store lives in the OS app-data directory and contains config.json, sessions, and messages.db. Override the location with TGCLI_STORE.

Legacy version: see MIGRATION.md.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.