# Compute Screener

> GPU cloud pricing (H100, H200, B200 per hour) and AI model API pricing per 1M tokens, with history.

- name: com.computescreener/compute-screener
- version: 1.21.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 78/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.computescreener%2Fcompute-screener
- tools: https://api.protogrid.dev/v1/servers/com.computescreener%2Fcompute-screener/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "compute-screener": {
      "type": "http",
      "url": "https://computescreener.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 97
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-94% +updated-10d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 78/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 94 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 14 of 14 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 3,670 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 50 (weight 15)

- warn `stability.changes`: 142 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them
- pass `stability.new_links`: no tool change named a new site

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 3,670 tokens to load them all
- tool set hash: 7ea04347da43cd08d1fb41a121f688b5
- tools last changed: 2026-11-13T20:43:40.035Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.computescreener/compute-screener.svg)](https://protogrid.dev/servers/com.computescreener/compute-screener)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-13 `fetch` changed (description)
  - before: 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, page:power, page:coding, page:datacenters) or the page's address: prices, changes, history, providers or models, as on the site.
  - after: The full text of a result from search, by its id (gpu:H100, company:OpenAI, model:<page>, provider:<page>, page:methodology (or one of its sections: page:methodology#compute, #tokens, #breakeven, #basis, #trending, #governance, #iosco), page:futures, page:verification, page:power, page:coding, page:datacenters, page:terms) or the page's address: prices, changes, history, providers or models, as on the site.
- 2026-11-13 `search` changed (outputSchema)
- 2026-11-13 `get_data_status` changed (description, outputSchema)
  - before: 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 latest days with a manifest.
  - after: 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, the latest days with a manifest, and the errata (each error found in a final value, with the correct value when it can be recomputed).
- 2026-11-13 `verify_price` changed (outputSchema)
- 2026-11-13 `list_indices` changed (outputSchema)
- 2026-11-13 `get_gpu_price_at` changed (outputSchema)
- 2026-11-13 `get_price_changes` changed (outputSchema)
- 2026-11-13 `get_model_prices` changed (description, inputSchema, outputSchema)
  - before: 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 usage share and its 1-month change. Give a model (name or page id, e.g. "Claude Opus 5.5" or "kimi-k3") for its daily price history as its page's chart draws it (a name several models share answers with each one's prices), or a company to list its models. Every other model OpenRouter prices is on the Every AI model page (https://computescreener.com/models): give its name or id (e.g. "meta-llama/llama-3.3-70b-instruct"), any company on it (e.g. "Cohere"), or every: true to list them, with sort: "price" for the cheapest input price first. For questions like "what does Claude Sonnet cost per 1M input and output tokens?", "the cheapest AI model API" or "the cheapest provider of a model".
  - after: 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 usage share and its 1-month change. Give a model (name or page id, e.g. "Claude Opus 5.5" or "kimi-k3") for its daily price history as its page's chart draws it (a name several models share, or a family's name such as "Qwen" or "GLM", answers with each one's prices), or a company to list its models. Every other model OpenRouter prices is on the Every AI model page (https://computescreener.com/models): give its name or id (e.g. "meta-llama/llama-3.3-70b-instruct"), any company on it (e.g. "Cohere"), or every: true to list them, with sort: "price" for the cheapest input price first. For questions like "what does Claude Sonnet cost per 1M input and output tokens?", "the cheapest AI model API" or "which provider serves a model cheapest" (its name, as the Every AI model page's Cheapest column shows it).
- 2026-11-13 `get_price_history` changed (outputSchema)
- 2026-11-13 `get_token_prices` changed (outputSchema)

Full history: https://api.protogrid.dev/v1/servers/com.computescreener%2Fcompute-screener/changes

## Remotes

- https://computescreener.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9350649)

## Packages

_none_

## Tools (14)

- `fetch`: The full text of a result from search, by its id (gpu:H100, company:OpenAI, model:<page>, provider:<page>, page:methodology (or one of its sections: page:methodology#compute, #tokens, #breakeven, #basis, #trending, #governance, #iosco), page:futures, page:verification, page:power, page:coding, page:datacenters, page:terms) or the page's address: prices, changes, history, providers or models, as on the site.
- `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, the latest days with a manifest, and the errata (each error found in a final value, with the correct value when it can be recomputed).
- `get_gpu_market_prices`: Rental prices of every other GPU, as the site's Every GPU page lists them (https://computescreener.com/gpus): A40, L4, V100, T4 and over 60 more, each one's lowest and median price per GPU-hour today as posted (offers that can be rented now), its offers, how many are in stock, its providers and the cheapest, from RunPod, Vast.ai, Akash, Shadeform's catalog of clouds, Lium, Vultr, AWS, Azure, Google Cloud, Oracle, Akamai, Koyeb, Packet, Northflank, Fireworks AI, Thunder Compute, DeepInfra, Replicate, Baseten, Lightning AI, Beam, fal, Exoscale, Atlantic.Net, Hugging Face, IBM Cloud, Novita AI, Oblivus, FriendliAI, Seeweb (posted in euros, converted at the ECB rate) and, from 2026-11-01, SaladCloud. Not an index: configurations are not standardized (the GPUs with a price index are in get_gpu_prices).
- `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 1D or 5D chart's range (the 1D chart in 10-minute intervals, the 5D chart in 30-minute intervals: the value in force at that mark), else the daily value of that US Central day.
- `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, RTX 6000 Ada, L40, RTX 5090, RTX 4090), with 1-day, 1-week and 1-month changes, the index day and a link to each GPU's page. Give one GPU to also get what its page shows: its benchmark contract, each provider's average price standardized to that contract, the posted prices of providers outside the index (AWS, Azure, Google Cloud, Oracle, Koyeb, Packet: each one's lowest, as posted) and its compute futures prices: each exchange listing a contract on its rental price, with the last price and 24-hour volume, refreshed every minute (all of them: https://computescreener.com/futures). For past values use get_price_history; for providers' posted prices get_provider_prices. For questions like "what does an H100 cost per hour?", "how much is it to rent a B200?" or "H200 cloud pricing today".
- `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 usage share and its 1-month change. Give a model (name or page id, e.g. "Claude Opus 5.5" or "kimi-k3") for its daily price history as its page's chart draws it (a name several models share, or a family's name such as "Qwen" or "GLM", answers with each one's prices), or a company to list its models. Every other model OpenRouter prices is on the Every AI model page (https://computescreener.com/models): give its name or id (e.g. "meta-llama/llama-3.3-70b-instruct"), any company on it (e.g. "Cohere"), or every: true to list them, with sort: "price" for the cheapest input price first. For questions like "what does Claude Sonnet cost per 1M input and output tokens?", "the cheapest AI model API" or "which provider serves a model cheapest" (its name, as the Every AI model page's Cheapest column shows it).
- `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 that time.
- `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, from 2026-10-23 for the other first GPUs and from its first index day for each GPU added later, weekly before; token history is daily from 2025-01-01. Give days for the latest days, or from and to for a period (e.g. a month: from 2026-01-01 to 2026-01-31).
- `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 benchmark contract so providers compare like for like. Give a provider (e.g. "CoreWeave", "RunPod") and/or a GPU; a provider outside the index (AWS, Azure, Google Cloud, Oracle and others) answers with its lowest posted price for each GPU, as the GPU's page lists it. For questions like "what does RunPod charge for an H100?", "AWS H100 price" or "Lambda GPU pricing".
- `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 company to also get its models' usage shares and posted input, cached input and output prices, and its estimated spend on OpenRouter. For one model's prices use get_model_prices; for past values get_price_history. For questions like "what does Claude cost per 1M tokens?" or "which AI company's API is cheapest?".
- `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 every GPU, or a company for its models; give a throughput for what the gross margin calculator on a model's page shows: the revenue per GPU-hour and the gross margin. For questions like "how many tokens per second must an H100 sell to cover its rent?".
- `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 provider or model count, its benchmark contract (GPUs) and its page, and the GPUs on the Every GPU page. Use it to see what the other tools accept.
- `search`: Search Compute Screener's pages by keyword: the GPUs, AI companies, AI models with a page, GPU providers, methodology, compute futures, wholesale electricity prices, AI coding tools and AI data center sites (e.g. "H100", "Claude Opus", "CoreWeave", "benchmark contract"). Returns ids for fetch, the page the query names first, and none when no page is about it. GPUs without an index and models without a page are on the Every GPU and Every AI model pages: get_gpu_market_prices and get_model_prices.
- `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 command that recomputes it from the public files with the published code. Omit date for the latest day with a manifest.