Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Cheap GPUs

REMOTE · CHEAP-GPUS.COM

Live GPU rental and LLM inference prices across dozens of providers, plus GPU price forecasts.

Available components

72 Trust /100

Last scanned (7 hours ago)

Scores higher than 58% of remote servers

Reachable. Last reached 5 Nov 2026.

Category AI and Machine Learning

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 754 tokens (~107/item across 7 items; 7 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management7
  • Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Stability: unverified → 0.03 ▲ functional
    • Tool “cheapest_gpu” changed its title: Cheapest GPU rentals cosmetic
    • Tool “cheapest_model_route” changed its title: Cheapest LLM providers cosmetic
    • Tool “find_model” changed its title: Find an LLM cosmetic
    • Tool “gpu_price_forecast” changed its title: GPU price forecast cosmetic
    • Tool “gpu_price_history” changed its title: GPU price history cosmetic
    • Tool “gpus_needed_for_model” changed its title: GPUs needed to host a model cosmetic
    • Tool “list_gpu_families” changed its title: List GPU families cosmetic
  • 3 Nov 26 71

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://cheap-gpus.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=cheap-gpus.com CN=WE1,O=Google Trust Services,C=US 18 Sept 2026 17 Dec 2026 ECDSA 256 ECDSA-SHA256 5c760c0161a444700e7365d540edcb93
SANs: cheap-gpus.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of cheap-gpus.com. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
cheap-gpus.com. present 2371 13 Verified
cheap-gpus.com. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src https://fonts.gstatic.com; img-src 'self' data:; connect-src 'self'; frame-ancestors 'none'; base-uri 'self'; form-action 'self'; object-src 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://cheap-gpus.com/mcp Verified 200
http (plaintext) http://cheap-gpus.com/mcp HTTPS enforced 301 https://cheap-gpus.com/mcp
MCP tools · 7 exposed · ~657 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
cheapest_gpu ~110

Cheapest current rental offers for one GPU family (e.g. "H100", "RTX 5090", "b200"), in USD per GPU-hour, cheapest first, one row per provider. pricing_type is "on_demand" (default; can't be interrupted) or "spot" (cheaper, the provider can reclaim the machine). limit: 1-10.

NameTypeReqDescription
gpustringyes–
limitinteger––
pricing_typestring––

Structured output declared, but exposes no named fields.

No examples provided.

cheapest_model_route ~114

Cheapest inference providers for one LLM (e.g. "deepseek-v3", "gpt-oss-120b"; use find_model if unsure of the name). Prices are USD per 1M tokens; estimated_cost_usd is for the given input/output token counts. One row per provider, cheapest first. limit: 1-10.

NameTypeReqDescription
input_tokensinteger––
limitinteger––
modelstringyes–
output_tokensinteger––

Structured output declared, but exposes no named fields.

No examples provided.

find_model ~83

Search the LLM catalog by name (e.g. "deepseek v3", "gpt-oss", "llama 70b"). Returns model slugs to pass to cheapest_model_route / gpus_needed_for_model, most widely offered first. limit: 1-10.

NameTypeReqDescription
limitinteger––
querystringyes–

Structured output declared, but exposes no named fields.

No examples provided.

gpu_price_forecast ~86

Market-implied future rental price for one GPU family (USD per GPU-hour), from prediction markets (Kalshi, Polymarket) and ICE futures, plus today's compute-index benchmarks and cheap-gpus.com's own current median price. Covers H100, H200, B200, A100 and RTX 5090.

NameTypeReqDescription
gpustringyes–

Structured output declared, but exposes no named fields.

No examples provided.

gpu_price_history ~65

Daily price history for one GPU family: each day's median across providers of each provider's cheapest offer (USD per GPU-hour). days: 1-90.

NameTypeReqDescription
daysinteger––
gpustringyes–
pricing_typestring––

Structured output declared, but exposes no named fields.

No examples provided.

gpus_needed_for_model ~152

How many GPUs it takes to self-host an open-weight LLM at a given quantization, and the cheapest rental setups for it right now. quant is one of: fp16, bf16, fp8, mxfp8, int8, q6, fp6, q5, q4km, nvfp4, awq, mxfp4, gptq, int4, q3, q2, iq2, iq1. Estimates memory only (weights + 20% runtime overhead), not throughput. limit: 1-10.

NameTypeReqDescription
limitinteger––
modelstringyes–
quantstring––

Structured output declared, but exposes no named fields.

No examples provided.

list_gpu_families ~47

List every GPU family tracked on cheap-gpus.com, with VRAM, live cheapest on-demand price (USD per GPU-hour), and how many providers currently offer it.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Cheap GPUs MCP server?

Cheap GPUs is a hosted endpoint at https://cheap-gpus.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · cheap-gpus.com

# add to Claude Code
claude mcp add --transport http com-cheap-gpus-cheap-gpus 'https://cheap-gpus.com/mcp'
Common questions

What is the Cheap GPUs MCP server?

Cheap GPUs is an MCP server listed in the public MCP registry as com.cheap-gpus/cheap-gpus. Live GPU rental and LLM inference prices across dozens of providers, plus GPU price forecasts. This page covers its hosted endpoint (https://cheap-gpus.com/mcp).

Is the Cheap GPUs MCP server safe to use?

Cheap GPUs scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Cheap GPUs MCP server expose?

Cheap GPUs exposes 7 tools: list_gpu_families, cheapest_gpu, gpu_price_history, find_model, cheapest_model_route, and 2 more. Their descriptions and schemas cost roughly 657 tokens of context every time the server is loaded.

Does the Cheap GPUs MCP server require authentication?

No. We connected to Cheap GPUs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Cheap GPUs MCP server still maintained?

Cheap GPUs is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.