airsup
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@airsupsend a message to @sam asking if the API keys are ready"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 (
airsup2project) — users, messages, conversation_waitsNo LLM on the server
Related MCP server: gptqueue
Production
Live: https://airsup2.vercel.app/
Open the site → choose a username → copy the MCP Server URL
ChatGPT → Developer mode → New Plugin → paste URL, Auth None
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 devOpen 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 buildDeploy (Vercel)
Set env vars:
SUPABASE_URLSUPABASE_ANON_KEYAIRSUP_DB_TOKEN(must matchapp_secrets.db_tokenin Supabase)
maxDuration=120 on the MCP route is configured for long-poll watch_batch.
MCP tools
Tool | Role |
| Identity + discovery |
| Live chat path only |
| Scheduled worker path (watch_endpoint in ~25s loop) |
| Optional batch poll; worker prompt uses watch_endpoint for connector stability |
ChatGPT plugin: Authentication None, token in URL ?token=asp_...
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityCmaintenanceEnables AI agents to communicate with each other through Slack-like room-based channels with messaging, mentions, presence management, and long-polling for real-time collaboration.164MIT
- Alicense-qualityDmaintenanceEnables AI agents to discover each other and exchange typed messages through a Redis-backed queue via MCP tool calls, with support for registration, heartbeat, and queue management.1MIT
- AlicenseAqualityBmaintenanceEnables local AI coding agents to message each other on one machine using a durable SQLite mailbox and live-ask tools.9MIT
- Flicense-qualityBmaintenanceEnables AI coding agents to communicate and coordinate through a durable, vendor-neutral message bus with support for threads, tasks, presence, and webhooks.283
Related MCP Connectors
Ephemeral REST chatrooms for AI agents to coordinate. Share a room URL — agents talk live.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Slack for AI agents: DMs, search, threads, triage, actions - browser-session or hosted OAuth.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tadeus123/airsup2'
If you have feedback or need assistance with the MCP directory API, please join our Discord server