telegram-mcp-notify
Enables AI coding agents to send structured Telegram notifications for events like questions, plan_ready, final, attention_needed, and error.
README
telegram-mcp-notify
Notify-only Telegram MCP server for AI coding agents (Cursor, Codex, Claude Code).
IMPORTANT DISCLAIMER (WIP / SELF-USE)
[!WARNING] This repository is still in active development and currently intended for personal/self use and experimentation. APIs and behavior may change without notice. Use at your own risk.
Breaking Changes in 0.2.0
- Removed console script:
telegram-mcp-listener - Removed reply/input internals (
inbox, listener lifecycle, pending prompts) - Removed singleton lock behavior for server startup
Features
- Outbound Telegram notifications for:
questionplan_readyfinalattention_needederror
- Notify-only MCP surface:
send_telegram_notificationtelegram_notify_capabilities
- Cross-platform runtime (Windows and POSIX)
Prerequisites
- Python 3.11+
uv/uvx(recommended) orpip- Telegram bot token (from @BotFather)
- Telegram chat ID
Quick Start: Cursor
Create .cursor/mcp.json in your project root (or ~/.cursor/mcp.json globally):
{
"mcpServers": {
"telegram_notify": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/hyper-tew/telegram-mcp-notify",
"telegram-mcp-notify"
],
"env": {
"TELEGRAM_BOT_TOKEN": "123456:ABC-DEF...",
"TELEGRAM_CHAT_ID": "123456789"
}
}
}
}
Restart Cursor after saving.
Quick Start: Codex
Add to ~/.codex/config.toml:
[mcp_servers.telegram_notify]
command = "uvx"
args = ["--from", "git+https://github.com/hyper-tew/telegram-mcp-notify", "telegram-mcp-notify"]
[mcp_servers.telegram_notify.env]
TELEGRAM_BOT_TOKEN = "123456:ABC-DEF..."
TELEGRAM_CHAT_ID = "123456789"
Or via CLI:
codex mcp add telegram_notify \
--env TELEGRAM_BOT_TOKEN=123456:ABC-DEF... \
--env TELEGRAM_CHAT_ID=123456789 \
-- uvx --from "git+https://github.com/hyper-tew/telegram-mcp-notify" telegram-mcp-notify
Alternative: Pre-install with pip
# From GitHub
pip install git+https://github.com/hyper-tew/telegram-mcp-notify.git
# From local clone
pip install ./telegram-mcp-notify
# Development
pip install -e "./telegram-mcp-notify[dev]"
Then use Python module mode in MCP config:
[mcp_servers.telegram_notify]
command = "python"
args = ["-m", "telegram_mcp_notify.server"]
[mcp_servers.telegram_notify.env]
TELEGRAM_BOT_TOKEN = "123456:ABC-DEF..."
TELEGRAM_CHAT_ID = "123456789"
Environment Variables
Required:
TELEGRAM_BOT_TOKENTELEGRAM_CHAT_ID
Optional:
| Variable | Default | Description |
|---|---|---|
TELEGRAM_PARSE_MODE |
None | Message parse mode (HTML or Markdown) |
TELEGRAM_DISABLE_NOTIFICATION |
false |
Suppress outbound notifications |
TELEGRAM_TIMEOUT_SECONDS |
10 |
HTTP request timeout |
Available Tools
| Tool | Description |
|---|---|
send_telegram_notification |
Send a structured Telegram checkpoint notification |
telegram_notify_capabilities |
Return current server tool/capability surface |
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
| No notifications received | Invalid token/chat ID | Verify TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID |
| Unexpected tools shown | Running old package version | Upgrade/restart MCP runtime |
spawn telegram-mcp-notify ENOENT |
Executable not on PATH | Use uvx ... telegram-mcp-notify or python -m telegram_mcp_notify.server |
spawn uvx ENOENT |
uv not installed/on PATH |
Install uv and restart the client app |
License
MIT
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.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.