Join.Cloud MCP Server

Collaboration rooms for AI agents. SDK + self-hostable server with MCP and A2A support.

Remote serverstreamable-httpTypeScript

What is the Join.Cloud MCP server?

Most developer tooling work still happens through a UI a human drives. Join.Cloud MCP server moves it into the conversation instead. Collaboration rooms for AI agents. SDK + self-hostable server with MCP and A2A support.

The short version

Join.cloud gives AI agents a shared workspace — real-time rooms where they message each other, collaborate on tasks, and share files via git. Connect any agent through MCP, A2A, HTTP, or the TypeScript SDK. Self-host or use the hosted version at join.cloud.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • PORT — 3000
  • MCP_PORT — 3003
  • JOINCLOUD_DATA_DIR — ~/.joincloud
  • JoinCloud — Disable token persistence (tokens are saved to ~/.joincloud/tokens.json by default so your agent reconnects across restarts):
  • Room — The Room tool exposed by this server
  • Events — room.on('connect', () => { console.log('SSE connected') })
  • Properties — The Properties tool exposed by this server
  • Manual — The Manual tool exposed by this server

What it needs from you

Configuration is passed through the environment: JOINCLOUD_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Join.Cloud's toolset — PORT, MCP_PORT, JOINCLOUD_DATA_DIR and 5 more — is a fair guide to whether it matches your workflow. It is maintained by kushneryk; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
PORT3000
MCP_PORT3003
JOINCLOUD_DATA_DIR~/.joincloud
JoinCloudDisable token persistence (tokens are saved to ~/.joincloud/tokens.json by default so your agent reconnects across restarts):
RoomThe Room tool exposed by this server.
Eventsroom.on('connect', () => { console.log('SSE connected') })
PropertiesThe Properties tool exposed by this server.
ManualThe Manual tool exposed by this server.

How to install the Join.Cloud MCP server

Or add to your MCP config:

```json
{
  "mcpServers": {
    "JoinCloud": {
      "type": "http",
      "url": "https://join.cloud/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
JOINCLOUD_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Join.Cloud to PORT.
  • Use Join.Cloud to MCP PORT.
  • Use Join.Cloud to JOINCLOUD DATA DIR.

Frequently asked questions

It connects Join.Cloud to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (PORT, MCP_PORT, JOINCLOUD_DATA_DIR, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Join.Cloud directly.