"This script ( mcp-server.js) acts as a local proxy. The agent communicates with it via stdio (standard), and the script makes HTTP requests to your Vercel backend, managing the question delivery and the polling (active waiting) for the response. Agent (Local) → calls ask_telegram_confirmation Local Proxy (mcp-server.js) → calls POST /api/confirm on Vercel Vercel → sends a message to the Telegram Bot"
"To add this server to your Antigravity configuration (or any MCP client), use the following JSON block. You need to replace: <ABSOLUTE_PATH> with the absolute path where you cloned this repository. <YOUR_VERCEL_URL> with your Vercel deployment URL (e.g., https://my-telegram-bot.vercel.app). git clone https://github.com/aralroca/telegram-bot-mcp.git cd telegram-bot-mcp npm install Talk to @BotFather to create a bot (/newbot). Save the BOT_TOKEN. Get your CHAT_ID (send a message to the bot and check https://api.telegram.org/bot<TOKEN>/getUpdates)."
An MCP agent uses a local proxy (mcp-server.js) to send confirmation requests to a Vercel backend. The Vercel backend forwards the question to a Telegram bot and records user replies in Upstash Redis. The local proxy actively polls Vercel for confirmation status so the agent receives the user response (e.g., "User replied: YES"). Deployment steps include cloning the repo, installing dependencies, configuring BOT_TOKEN, CHAT_ID, and ALLOWED_USER_ID, deploying to Vercel, adding Upstash Redis, and setting the Telegram webhook. Vercel Deployment Protection must be disabled to allow the local proxy to call the endpoints.
Read at GitHub
Unable to calculate read time
Collection
[
|
...
]