telegram-mcp
Enables AI agents to read, send, and organize Telegram messages and chats. Supports tools for listing chats, fetching messages, sending/reply, archiving, muting, and folder management.
README
telegram-mcp
Telegram MCP server that gives AI agents full access to your chats, channels, and groups. Works with any MCP-compatible client (Claude Code, Cursor, etc.). Built with Telethon.
Read messages, send replies, and organize your Telegram: auto-categorize channels into folders, mute noisy chats, archive stale ones, and clean up subscriptions. See AGENTS.md for ready-to-use workflows.
What can it do?
Read - list chats/channels/groups, fetch and search messages, get chat details
Write - send, edit, delete, and forward messages, pin/unpin, mark as read
Organize - archive/unarchive, mute/unmute, create and manage chat folders
AI Workflows
The tools are designed to work together for multi-step organization tasks. AGENTS.md includes ready-to-use workflows:
- Auto-organize channels into folders - fetch all channels, sample recent messages to infer topics, group into themed folders
- Identify cleanup candidates - find inactive or high-unread channels, suggest archive/mute/unsubscribe
- Triage unread messages - summarize what's important across chats, bulk mark-read the rest
- Reorganize existing folders - audit folder structure, find uncategorized chats, restructure
Setup
1. Get Telegram API credentials
Go to my.telegram.org/apps and create an application. You'll get an API_ID and API_HASH.
2. Install
git clone https://github.com/VovaVindar/telegram-mcp.git
cd telegram-mcp
python3 -m venv .venv
.venv/bin/pip install -e .
3. Configure
cp .env.example .env
# Edit .env with your API_ID and API_HASH
4. Authenticate
.venv/bin/python3 telegram_mcp_server.py
Scan the QR code with your Telegram app (Settings > Devices > Link Desktop Device). This creates a telegram.session file that stores your auth state.
5. Connect to Claude Code
The .mcp.json file registers the server automatically. Just open Claude Code in this directory and the tools will be available.
To use it from any directory, add this to your ~/.claude/claude_code_config.json:
{
"mcpServers": {
"telegram-mcp": {
"command": "/absolute/path/to/telegram-mcp/.venv/bin/fastmcp",
"args": ["run", "/absolute/path/to/telegram-mcp/telegram_mcp_server.py"]
}
}
}
Available Tools
| Tool | Description |
|---|---|
list_dialogs |
List chats/channels/groups with optional filter |
get_messages |
Fetch messages (use "me" for Saved Messages) |
search_messages |
Search messages by text, optionally within a chat |
get_chat_info |
Get details about a chat or user |
send_message |
Send a message (supports reply) |
edit_message |
Edit an existing message |
delete_messages |
Delete messages by ID |
forward_messages |
Forward messages between chats |
archive_chat |
Archive a chat |
unarchive_chat |
Unarchive a chat |
pin_message |
Pin a message in a chat |
unpin_message |
Unpin a message |
mark_read |
Mark all messages in a chat as read |
mute_chat |
Mute a chat (optionally for N hours) |
unmute_chat |
Unmute a chat |
list_folders |
List all chat folders |
create_folder |
Create a new folder with specified chats |
update_folder |
Rename or modify folder chats |
delete_folder |
Delete a folder |
Tips
- Use
chat_id="me"to target Saved Messages - Paginate with
offset_id: pass the last message ID from the previous batch - Folder names are limited to 12 characters by Telegram
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。