readygpu MCP server

• Registry namecom.readygpu/readygpuverified in the MCP registry

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

• Stateanswerschecked 2026-10-29
• Tools6
• Server calls itselfreadygpu
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 558 ms.

• Its tools do every use case we checked: Check which GPUs run a chosen model; Estimate tokens per second for local models; Compare used graphics cards by price and speed.
• Checked on 4 of the 7 days it takes to judge reliability.

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.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer597 ms
• Space in an agent's context≈ 1,465 tokensthe definitions of all its tools (6), which an agent carries on every turn
• Tool definitionsA · 94 of 100
• Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 2 of 6

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 →

• search_models

  Find open-weight AI models by name or task (chat, coding, agentic, vision, reasoning). Returns each model's slug, size, context length and licence; use the slug with hardware_for_model.

• find_hardware

  List graphics cards or complete machines (Macs, mini PCs) sold in a market, with memory, bandwidth, the estimated speed on a model and a link to each one's page and prices. Filter by minimum memory and new or used; sort by speed or…

• hardware_details

  One graphics card or machine in a market: its specifications, which models it runs fully in memory at a context length and how fast, and a link to its page and prices.

• hardware_for_model

  For one model: how much memory it needs at each context length, and the fastest hardware (and the fastest Mac) that runs it fully in memory in a market, with their speeds. Links the model's page, which shows the cheapest and best-value…

• best_hardware

  The ranked 'best for local AI' lists of a market (all graphics cards, cards under a price, used cards, Macs and mini PCs): best first by the most capable model each runs fully in memory. Prices are on each list's page.

• compare_hardware

  Two graphics cards or machines side by side in a market: memory, bandwidth, how many models each runs fully in memory, and the estimated speed of each on every model.