MCP.Market

Gpusmarket MCP server

online · 100% uptime
by jyswee·io.github.jyswee/gpusmarket·v2.4.16·1 stars

Rent real GPUs from the terminal. Per-second billing, $0.50 minimum. stdio MCP server.

A85/100grade A
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

1 stars158 downloads/wk

Reviews

Write one

Nobody has reviewed Gpusmarket yet.

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

Gpusmarket tools (2, 1 write)

write = sends, deletes, buys or posts
  • gpusmarket_get_startedFree

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

  • gpusmarket_signupwrite actionFree

    Create a new GPUsMarket account. Requires the human's email. Returns an API key (shown once) and unlocks all GPUsMarket tools in this session immediately. To rent, the human adds a card via secure Stripe checkout — nothing is charged to sign up. Ask the human for their email before calling.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan18 source files scanned25/25
  • Live reliabilityremote reachable in 2289ms17/20
  • Tool poisoning2 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 38 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Gpusmarket compares

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

Safety score
85/100
higher than 70% of 48,255 servers
Tools
2
the typical server has 7
Tools that change things
50%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
136 ms
faster than 76% of 30,031 servers
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
158
more than 71% of 12,191 servers with a package

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

Install Gpusmarket in Claude Code, Cursor or VS Code

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

What the publisher says

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

gpusmarket

Rent real GPUs from the terminal. Built for AI agents.

One command to sign up, one to rent, one to run inference. Per-second billing, no subscriptions, $0.50 minimum per rental. The CLI your coding agent can drive end-to-end: GPUsMarket.

npm install for GPUs. One command in, one command out.

Renting a GPU usually means a signup form, a quota request, a support ticket, and a $50 minimum — before you've run a single token. GPUsMarket collapses that to three commands: everything from consumer RTX 4090s to datacenter H100s and MI300Xs, rentable by the second. And it's built so your agent can sign up and rent by itself — no human, no browser, no dashboard.

Works with: Claude Code · Cursor · Cline · Windsurf · Aider · Codex · any MCP client

<!-- HERO: money loop — install → signup → search → rent → chat (real inference) → stop → per-second bill -->

Install to real inference in under a minute — watch the full-res demo.

npm install -g gpusmarket
gpusmarket init

Quick start

# Create an account (returns your API key, auto-saved)
gpusmarket signup --email you@example.com --tenant my-agent

# Find a GPU
gpusmarket search --gpu "RTX 4090"

# Rent the cheapest match — returns an OpenAI/Ollama-compatible endpoint + key
gpusmarket rent --gpu "RTX 4090"

# Run inference straight through your rental
gpusmarket chat "What is 2+2?" --model gemma3:4b

# Stop when done — you pay for exactly the seconds you used
gpusmarket stop RENTAL-ID

Built for agents

Built so an agent can go from zero to running inference with no human in the loop — sign up, rent, infer, and stop, all from the terminal or over MCP. This CLI is designed to be driven by AI coding agents (Claude Code, Cursor, Cline, Windsurf, Codex, Copilot), not just humans.

  • gpusmarket init — in-terminal quickstart: detects your agent's config file, prints a ready-to-paste skill block, MCP setup, and next steps.
  • gpusmarket init --agent-schema — the full command contract as JSON: every command, every flag, plus the rules agents must follow. Load it into context and your agent never hallucinates a flag.
  • --json everywhere — every command has machine-readable output.
  • Zero dependencies — a single self-contained Node.js CLI. Nothing to audit but us.

Watch an agent drive it end-to-end (click for the full-res video):

Claude Code searches, rents, runs inference, and stops the GPU — no human in the loop.

MCP server

gpusmarket mcp-serve exposes 32 tools over stdio — search, rent, status, stop, chat, host, pools, the whole surface. Add it to Claude Code:

claude mcp add gpusmarket -- gpusmarket mcp-serve

…or drop it into any MCP client's .mcp.json. The MCP server runs outside your project directory, so pass your API key via the GPUSMARKETAPIKEY environment variable:

Shortened. The full README is on GitHub.

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

Gpusmarket: common questions

Is Gpusmarket MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Gpusmarket safety report
How do I install Gpusmarket?
It runs remotely at mcp.gpusmarket.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 Gpusmarket need an API key?
Yes. The registry entry asks for GPUSMARKET_API_KEY, Authorization.
Is Gpusmarket maintained?
The last commit was 38 days ago (2026-09-27). The latest release is v2.4.16.
Is Gpusmarket up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Gpusmarket compare with other MCP servers?
safety score 85/100 (higher than 70% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from jyswee →