Servidor MCP de Compute Screener

• Nome no registrocom.computescreener/compute-screenerverificado no registro MCP

O nome no registro fica sob computescreener.com. O registro só libera esse espaço de nomes para quem prova controle do domínio por DNS ou HTTP.

• Estadorespondeverificado em 2026-10-29
• Ferramentas14
• O servidor se chamacomputescreener
• Versão do servidor1.16.1
• Versão do protocolo2025-06-18

Em 2026-10-29 o servidor respondeu a initialize e tools/list sem login. Primeira resposta em 730 ms.

• As ferramentas fazem todos os casos de uso verificados: compare hourly on-demand GPU rental prices across providers; track AI token prices by model and lab.
• Verificado em 5 dos 7 dias necessários para julgar a confiabilidade.

Dito por regras a partir das medições acima. A primeira chamada provável é a escolha de um modelo na lista de ferramentas; leia a descrição antes de confiar nela.

• Nota INITE MCPdepois de uma semanaa nota precisa de 7 verificações diárias: 5 até agora
• O que um agente consegue fazer com ele2 de 2 casos de uso
• Respondeumedindo5 das 7 verificações diárias necessárias para mostrar a porcentagem
• Mediana da primeira resposta666 ms
• Espaço no contexto do agente≈ 2.921 tokensas definições de todas as ferramentas (14), que o agente carrega a cada turno
• Definições das ferramentasA · 100 de 100
• Resultados tipados14 de 14 ferramentasdeclaram outputSchema: o resultado chega tipado e é lido de uma vez

• Todas as ferramentas passam nas seis verificações.

Um programa verifica o servidor uma vez por dia: initialize e tools/list, sem modelo. Os tokens são o tamanho das definições, a cerca de quatro caracteres por token. A nota é a média de seis verificações do nome, da descrição, do esquema e das anotações de cada ferramenta; diz se as ferramentas estão bem descritas, não se funcionam. A nota pesa só o que foi medido: se responde (25%), se faz o trabalho do produto (25%), definições (20%), contexto (10%), uso (10%) e a facilidade de conectar (10%). Uma parte não medida fica de fora, e uma instrução oculta limita a nota a 40. O estado dos servidores MCP dos fornecedores: método e números →

• get_gpu_prices

  Today's GPU rental prices: the price index in USD per GPU-hour for each GPU (H100, H200, A100, B200, B300, RTX PRO 6000, L40S, RTX A6000), with 1-day, 1-week and 1-month changes, the index day and a link to each GPU's page. Give one GPU…

• get_token_prices

  Today's AI token prices by company: each company's price index in USD per 1M tokens at the mix of tokens agents send (87% cache read, 12% input, 1% output), weighted by its models' usage, with 1-day, 1-week and 1-month changes. Give one…

• get_price_history

  Price history of one GPU (USD per GPU-hour) or one AI company (USD per 1M tokens), oldest first. GPU history is daily from 2025-11-07 for H100 and A100 and from 2026-10-23 for the others, weekly before; token history is daily from…

• get_model_prices

  Each AI model's posted API prices in USD per 1M input, cached input and output tokens and its price at the mix of tokens agents send (the models behind the token index and the Intelligence Index chart's, each with its page), with its…

• get_provider_prices

  Each GPU cloud's and marketplace's posted on-demand prices per GPU, as its page on the site shows them (lowest and highest that day, as posted, with the configuration of the lowest) and its average in the index, standardized to the GPU's…

• get_price_changes

  What moved, as the site's changes show it: every listed GPU and company index's change over 1, 5, 7 or 30 days (the site's 1D, 5D, 1W and 1M), largest first, and every AI model whose price (at the mix, as its page charts it) moved over…

• get_gpu_market_prices

  Rental prices of every other GPU, as the site's Every GPU page lists them (https://computescreener.com/gpus): RTX 5090, RTX 4090, RTX 6000 Ada, L40, A40, L4, GH200, V100 and over 60 more, each one's lowest and median price per GPU-hour…

• get_gpu_price_at

  A GPU's index price at a past date or time, as its page's chart draws it: the value calculated at or just before an ISO time within the last few days (the 1D and 5D charts; prices are recalculated every minute, kept at least every 30…

• get_workload_cost

  Break-even throughput, as each GPU's and each model's page shows it: the tokens per second one GPU must sell at a model's list price (3 input : 1 output) to cover the GPU's rental price today. Give a GPU for every model on it, a model for…

• list_indices

  Every GPU rental index and AI company token index the site lists: whether it is listed (has a price, a month of history and a value for each of its 1-day, 1-week and 1-month changes), its latest value and day, when its history starts, its…

• verify_price

  How a published daily value can be checked: whether it is final, and for a final day its manifest (every file it was computed from with its SHA-256, the factors in force, the calculation code's SHA-256 and the final values) and the…

• get_data_status

  How fresh the data is, as the status page shows it: when the GPU and token indices were last calculated, today's index day, each GPU price source's status and last read, each GPU index's status, provider count and imputed share, and the…

• search

  Search Compute Screener's GPUs, AI companies, AI models, GPU providers and methodology by keyword (e.g. "H100", "Claude Opus", "CoreWeave", "benchmark contract"). Returns ids for fetch.

• fetch

  The full text of a result from search, by its id (gpu:H100, company:OpenAI, model:<page>, provider:<page>, page:methodology, page:futures, page:verification) or the page's address: prices, changes, history, providers or models, as on the…