Skip to content
Cheap GPUs logo

Cheap GPUs MCP server

Which MCP servers are Cheap GPUs's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-11-03

← Back to Cheap GPUs

Whose server it is
  • Registry namecom.cheap-gpus/cheap-gpusverified in the MCP registry

The registry name sits under cheap-gpus.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-03
  • Stateanswerschecked 2026-11-03
  • Tools7
  • Server calls itselfcheap-gpus
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 302 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: compare hourly rental prices for each GPU model; track GPU rental price trends over 7 to 90 days.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "compare hourly rental prices for each GPU model", the likely first call is list_gpu_families.
  • For "track GPU rental price trends over 7 to 90 days", the likely first call is gpu_price_history.
  • Parameters are untyped or undescribed in 6 of 7 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-11-03
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer367 ms
  • Space in an agent's context≈ 920 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsB · 86 of 100
  • Typed results7 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 7

What an agent can do with it

  • can do · compare hourly rental prices for each GPU model
  • can do · track GPU rental price trends over 7 to 90 days
  • not sure · view a price heatmap across GPU families

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers7 tools · read 2026-11-03
  • list_gpu_families

    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.

  • cheapest_gpu

    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…

  • gpu_price_history

    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.

  • find_model

    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.

  • cheapest_model_route

    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…

  • gpu_price_forecast

    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…

  • gpus_needed_for_model

    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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "cheap-gpus": {
      "type": "http",
      "url": "https://cheap-gpus.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http cheap-gpus https://cheap-gpus.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://cheap-gpus.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.