mcpbeat Sign in

Xcelsior GPU Cloud MCP Server

answering

Xcelsior GPU Cloud is answering right now. Last checked 10 min ago. 6 installs a week from npm. Last commit 7 Nov 2026.

Rent GPUs, launch spot instances and run serverless inference on the Xcelsior marketplace.

Installs per day peak 173 · avg 6 · -57% w/w
a month agotoday
Uptime history 72 hours of history
72 hours agonow
100.0%
Uptime 24h
91 of 91 checks
—
Tools
hidden behind auth
135 ms
Response time
average over 24h
6
Installs / week
npm and PyPI

What the code does

We read the source, 1 h ago · rules 995398eba69f

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a dangerous call attach_volume.job_id → workers/worker_agent.py:1907, attach_volume.job_id → workers/worker_agent.py:1984, attach_volume.volume_id → workers/worker_privileged.py:179 и ещё 6
                inspect = subprocess.run(
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Deletes files or strips permissions workers/volumes.py:881
                f"mkfs.ext4 -q -L vol-{volume_id[:8]} /dev/mapper/{safe_mapper}",
Checks whether it runs in a sandbox billing/bitcoin.py:48, workers/volumes.py:124
    return os.path.exists("/.dockerenv")
Executes code built at runtime api/mcp/src/rate-limit.ts:63
    const result = await client.eval(INCREMENT_WITH_TTL_LUA, {
Builds a database query by concatenation api/templates/dashboard.html:1424
        <select id="alert-mining-thresh">
          <option value="0.8">High (80%+ util for 5 min)</option>
                shell=True,
Secret passed into the image build api/frontend/Dockerfile:22
ARG NEXT_PUBLIC_POSTHOG_PROJECT_TOKEN=
ARG NEXT_PUBLIC_POSTHOG_HOST=https://us.i.posthog.com
…hsJrHbfI2als+m+IHJKtNs8oBAAA="},"3c8bd1f7-3c21-4fb0-8bd7-f7353e1235f7":{"mime":"image/svg+xml","compressed":true,"data":"H4sIAAAAAAAAE21XS48bNwz+K4J71ixfoqRidw89jw+6+lYgaXaBtAmaRTY/vyCpseU0Ptj8Zii+9JGSH799/5R+/P35n29Pp5e3t6+/Pzy8v79v77x9+ffTAwHAw7fvn07p++vH9z++/Hg65bJJylhwa6lW2CC…
      - /var/run/docker.sock:/var/run/docker.sock:ro
            "/data/.ssh/known_hosts",
Page executes code built at runtime api/templates/dashboard.html:1923
  document.getElementById('hosts-table').innerHTML = d.hosts.map(h => {
Sends data to a third-party sink workers/scheduler.py:2836
        url = f"https://api.telegram.org/bot{cfg['telegram_bot_token']}/sendMessage"

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add xcelsior --transport http https://mcp.xcelsior.ca/mcp
Settings → Connectors → Add custom connector, then paste this address
https://mcp.xcelsior.ca/mcp
~/.codex/config.toml
[mcp_servers.xcelsior]
url = "https://mcp.xcelsior.ca/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "xcelsior": {
      "url": "https://mcp.xcelsior.ca/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "xcelsior": {
      "type": "http",
      "url": "https://mcp.xcelsior.ca/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Endpoints

URLTransportStateLatencyChecked
https://mcp.xcelsior.ca/mcp streamable-http sign-in 182 ms 10 min ago

Alternatives to Xcelsior GPU Cloud

same job, measured the same way
LoopSkill
by wisechef-ai

Search, install and compose AI agent skills, loops and bundles from the LoopSkill marketplace.

answering
Payzilla Marketplace
by payzilla

Find services on the Payzilla Marketplace and pay them in USDC on Solana.

4 tools answering
Gameye
by gameye

Launch, inspect and stop multiplayer game server sessions on Gameye from any MCP client.

106 installs/wk local only
Skillflow
by rafsilva85

Search, discover, and install 500+ AI agent skills from the SkillFlow marketplace.

70 installs/wk local only
Runpod
by mcparmory

Launch, scale, and manage GPU pods and serverless endpoints across regions

210 installs/wk local only
Marketplace
by vdappdev2

MCP server for Verus on-chain marketplace — create, browse, accept, and close offers

60 installs/wk local only
Marketplace
by bookingmaven

Book, reschedule and cancel appointments at any business on the BookingMaven marketplace.

11 tools answering
Purple Grain
by purplegrain

Search and book agricultural contracting services on the Purple Grain marketplace.

answering

Xcelsior GPU Cloud — questions

Answers built from our own checks of this server.

Why is there no tool list for Xcelsior GPU Cloud?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is Xcelsior GPU Cloud working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 135 ms. The bar chart above shows every period we have measured.
How do I connect Xcelsior GPU Cloud?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to Xcelsior GPU Cloud?
No API key is involved. Xcelsior GPU Cloud answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is Xcelsior GPU Cloud?
It answers our handshake in 135 ms on average, which is faster than 88% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Xcelsior GPU Cloud?
The npm package @xcelsior-gpu/mcp was installed 6 times in the last week. Week over week that is -57%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Xcelsior GPU Cloud open source?
The code is open source: it is published under the MIT licence, written in Python, 2 stars on GitHub and 6 open issues. The licence covers the code in the repository, not the hosted service at mcp.xcelsior.ca, which runs on its operator's own terms.