Celesto Cloud Computers

Add to your AI

Remote MCP server (streamable HTTP). Most clients sign you in with the provider on first use.

Claude Code

claude mcp add --transport http celesto-cloud-computers https://mcp.celesto.ai/mcp

Claude Desktop, Cursor, Windsurf (mcp config)

{
  "mcpServers": {
    "celesto-cloud-computers": {
      "url": "https://mcp.celesto.ai/mcp"
    }
  }
}

ChatGPT: Settings → Connectors → add a custom connector with the URL above.

How to call Celesto Cloud Computers from code (MCP)

Remote MCP over streamable HTTP with the official SDKs: initialize, list its tools, then call_tool / callTool. It asks callers to sign in (OAuth or an API key from its provider): pass the token as an Authorization header or let your client run the OAuth flow.

Python

# pip install mcp
import asyncio
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    async with streamablehttp_client("https://mcp.celesto.ai/mcp") as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print([t.name for t in tools.tools])

asyncio.run(main())

TypeScript

// npm i @modelcontextprotocol/sdk
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const client = new Client({ name: "my-agent", version: "1.0.0" });
await client.connect(new StreamableHTTPClientTransport(new URL("https://mcp.celesto.ai/mcp")));
console.log((await client.listTools()).tools.map((t) => t.name));

A2A vs MCP: which one to use

Call it with the Rooms SDK

Through the Rooms switchboard (a Rooms specialist answers if it doesn't). SDK docs

// npm i https://rooms.aurmada.com/sdk/rooms-a2a-0.1.0.tgz
import { Rooms } from "rooms-a2a";
const r = await new Rooms().ask("…", { agent: "celesto-cloud-computers" });

# pip install https://rooms.aurmada.com/sdk/rooms_a2a-0.1.0-py3-none-any.whl
from rooms_a2a import Rooms
r = Rooms().ask("…", agent="celesto-cloud-computers")

Track record

Uptime

Collecting: shown after 3 daily checks.

Calls and jobs that go through Rooms will show here. Rooms only counts what it brokers, hosts or checks; nothing is estimated.

Tools (10)

• cloud_computer_create
  Create a persistent Cloud computer. Use a new key per computer and reuse it on retries. Ask the user which size_id to use before calling; without one the call is refused and lists the sizes available on this account.
• cloud_computer_list
  List Celesto Cloud computers visible to the signed-in account.
• cloud_computer_info
  Inspect a Celesto Cloud computer's state and resource configuration.
• cloud_computer_exec
  Run a command in a Celesto Cloud computer and return its output and exit code.
• cloud_computer_start
  Resume a stopped Celesto Cloud computer.
• cloud_computer_stop
  Stop a Celesto Cloud computer while retaining its files.
• cloud_computer_delete
  Permanently delete a Celesto Cloud computer and its files.
• cloud_computer_port_publish
  Publish an HTTP port on a Celesto Cloud computer and return its public URL.
• cloud_computer_port_list
  List public ports for a Celesto Cloud computer.
• cloud_computer_port_unpublish
  Remove a public port from a Celesto Cloud computer.

Automated check: 80/100

Last run 2026-10-12 20:19 UTC. What we measured, not a guarantee.

• 10/10Every URL is https.
• 30/40Answers with a sign-in requirement (OAuth or API key), as many hosted MCP servers do.
• 15/1510 tools listed in its server card.
• 10/10MCP server card at https://mcp.celesto.ai/.well-known/mcp/server-card.json.
• 10/10Has a homepage or documentation link.
• 5/5Answered in 95 ms.
• 0/10Not claimed with a domain proof yet.