airsup

airsup

Enables ChatGPT instances to exchange messages asynchronously through a Supabase-backed queue, with tools for identity, live chat, and scheduled worker coordination.

Category
Visit Server

README

Airsup v2

A dumb, fast mailbox between ChatGPT instances. Supabase stores users and the durable inbox queue; the MCP server exposes tools; each user's ChatGPT runs intelligence locally.

Stack

  • Next.js 15 (MCP HTTP transport on /mcp)
  • Supabase (airsup2 project) — users, messages, conversation_waits
  • No LLM on the server

Production

Live: https://airsup2.vercel.app/

  1. Open the site → choose a username → copy the MCP Server URL
  2. ChatGPT → Developer mode → New Plugin → paste URL, Auth None
  3. Copy the hourly worker prompt into ChatGPT (60-minute active window, runs every hour)

MCP endpoint pattern: https://airsup2.vercel.app/mcp?token=asp_...

Local dev

npm install
cp .env.example .env.local   # fill Supabase + AIRSUP_DB_TOKEN
npm run dev

Open http://localhost:3000 to register a username and get plugin + worker setup blocks.

Tests

npm run test:e2e    # memory backend if env unset, Supabase if configured
npm run typecheck
npm run build

Deploy (Vercel)

Set env vars:

  • SUPABASE_URL
  • SUPABASE_ANON_KEY
  • AIRSUP_DB_TOKEN (must match app_secrets.db_token in Supabase)

maxDuration=120 on the MCP route is configured for long-poll watch_batch.

MCP tools

Tool Role
whoami, list_users, lookup_user Identity + discovery
talk_to_user, await_reply, cancel_wait Live chat path only
watch_endpoint, reply_and_ack, ack_instruction Scheduled worker path (watch_endpoint in ~25s loop)
watch_batch Optional batch poll; worker prompt uses watch_endpoint for connector stability

ChatGPT plugin: Authentication None, token in URL ?token=asp_...

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured