MCP.Market

Computegpu MCP server

online · 100% uptime
by jyswee·io.github.jyswee/computegpu·v1.2.1·1 stars
No reviews yet

Rent cloud GPUs from your agent: live catalogue, deploy, stop, destroy. Per-second billing.

B76/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B76/100

full report

Adoption
New

1 stars2 downloads/wk

Reviews

Write one

Nobody has reviewed Computegpu yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Computegpu tools (2, 1 write)

write = sends, deletes, buys or posts
  • computegpu_get_startedFree

    Explains what ComputeGpu is and how to activate this MCP server (no API key on this session yet).

  • computegpu_signupwrite actionFree

    Create a ComputeGpu account. Requires the human's email. Returns an API key (shown once) and unlocks all ComputeGpu tools in this session. Before the first deploy the owner verifies a card ($0, no charge). Ask the human for their email before calling.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

1 medium
  • Code scan15 source files scanned20/25
  • Live reliabilityremote reachable in 2081ms17/20
  • Tool poisoning2 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 130 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumHeavily hex-escaped string (obfuscation)obf.hex-density
    dist/account.js: …94));function _0x4840(){var _0x4e347c=['\x57\x36\x70\x63\x4b\x53\x6f\x75\x57\x37\x30\x66\x44\x78\x5a\x64\x54\x43\x6b\x56\x41\x53\x6b\x75\x41\x71','\x6a\x76\x38\x4b\x62\x31\x37\x63\x4d\…
Overall 76/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Computegpu compares

Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
76/100
higher than 43% of 1,119 Developer tools servers
Tools
2
the typical Developer tools server has 7
Tools that change things
50%
typical: 5%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote Developer tools server answers 100%
Response time
154 ms
faster than 67% of 443 Developer tools servers
GitHub stars
1
more than 50% of 855 Developer tools servers
Downloads a week
2
more than 0% of 436 Developer tools servers with a package

What its tools let an agent do: 1 read · 1 change

Install Computegpu in Claude Code, Cursor or VS Code

claude mcp add --transport http computegpu https://mcp.computegpu.com/mcp
Add to Cursor

What the publisher says

From the Computegpu repository's README, as published. We do not edit it. Read it on GitHub

computegpu

Rent cloud GPUs from your terminal. Deploy in 30 seconds.

npm i -g computegpu
computegpu signup you@company.com my-agent
computegpu deploy --gpu "RTX 4090"

Install

npm i -g computegpu

Requires Node.js 18+.

Quick Start

# Create account
computegpu signup you@company.com my-project

# Browse GPUs
computegpu types

# Deploy
computegpu deploy --gpu "RTX 4090" --models llama3.3

# Check status
computegpu pods
computegpu status POD_ID

# Stop
computegpu stop POD_ID

Commands

Deploy Options

computegpu deploy --gpu "RTX 4090"           # on-demand
computegpu deploy --gpu "RTX 4090" --spot    # 50% off (preemptible)
computegpu deploy --gpu "H100" --count 4     # multi-GPU
computegpu deploy --gpu "RTX 4090" --models llama3.3,gemma4  # pre-load models
computegpu deploy --gpu "RTX 4090" --type docker  # Docker + SSH
computegpu deploy --gpu "RTX 4090" --volume 100   # persistent storage

Config

API key is saved to ~/.computegpu/config.json (global) or ./.computegpu/config.json (local).

Priority: --key flag > COMPUTEGPUAPIKEY env > local config > global config.

computegpu login --key gpu_your_key          # save globally
computegpu login --key gpu_your_key --local  # save per-project
computegpu config                             # show active config

Pricing

47 GPU models. Per-second billing. $1 minimum top-up.

  • Consumer: RTX 3060 ($0.22/hr) to RTX 5090 ($1.24/hr)
  • Datacenter: A40 ($0.64/hr) to H200 ($10.76/hr)
  • Spot: 50% off (preemptible with 5-min warning)

Links

  • Website: computegpu.com
  • Docs: computegpu.com/docs
  • API: computegpu.com/.well-known/openapi.json

License

Proprietary. Copyright (c) 2026 Tyga.Cloud Ltd. See LICENSE.

Nothing above is checked by us. What we check is on the safety report.

Computegpu: common questions

Is Computegpu MCP server safe?
Mostly: it is graded B (76/100). Read the Computegpu safety report
How do I install Computegpu?
It runs remotely at mcp.computegpu.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Computegpu need an API key?
Yes. The registry entry asks for COMPUTEGPU_API_KEY, Authorization.
Is Computegpu maintained?
The last commit was 148 days ago (2026-06-09). The latest release is v1.2.1.
Is Computegpu up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Computegpu?
Servers from other publishers that do the same job: Dockhold MCP server, TerraVision MCP server and Agent Harnesses MCP server.
How does Computegpu compare with other Developer tools MCP servers?
safety score 76/100 (higher than 43% of 1,119 Developer tools servers); tools 2 (the typical Developer tools server has 7); tools that change things 50% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Computegpu

Same job from other publishers: the closest match first, then the best rated.

  • Dockhold
    Deploy your project to a live HTTPS URL from your AI tool; read logs, set variables, resize apps.
    A
  • TerraVision
    Draw cloud architecture diagrams with official AWS, Azure and GCP icons from a prompt or Terraform.
    A
  • Agent Harnesses
    Agent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.
    A
  • walkerOS Flow
    Build, validate, simulate, and deploy walkerOS event pipelines
    B
  • Omnara
    Deploy durable AI agents with Omnara, an open-source managed-agent platform.
    A

More from jyswee →