# Compute Screener (remote · computescreener.com)

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

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `computescreener.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-computescreener-compute-screener/computescreener.md), [page](https://verifymcp.io/servers/com-computescreener-compute-screener/computescreener)

## Channel facts

- Endpoint: `https://computescreener.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.21.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3126 tokens (~195/item across 16 items; 14 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Compute Screener MCP server?

Compute Screener is a hosted endpoint at https://computescreener.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.

### Claude

```bash
claude mcp add --transport http com-computescreener-compute-screener 'https://computescreener.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.com-computescreener-compute-screener]
url = "https://computescreener.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-computescreener-compute-screener": {
      "type": "remote",
      "url": "https://computescreener.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-computescreener-compute-screener --url 'https://computescreener.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-computescreener-compute-screener:
    url: "https://computescreener.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-computescreener-compute-screener": {
      "Transport": "http",
      "Url": "https://computescreener.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-computescreener-compute-screener -t streamable-http -u 'https://computescreener.com/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_model_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_price_history” rewrote its description, which is the text the model reads
- [security] Tool “get_provider_prices” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 174 → 195
- [functional] Server version: 1.19.0 → 1.21.0
- [cosmetic] “get_model_prices” added an optional parameter “limit”
- [cosmetic] “get_model_prices” added an optional parameter “sort”
- [cosmetic] “get_price_history” added an optional parameter “from”
- [cosmetic] “get_price_history” added an optional parameter “to”
- [cosmetic] “get_model_prices” reworded the description of “company”

### 2026-11-03 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 75, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_gpu_market_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_gpu_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_model_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_price_history” rewrote its description, which is the text the model reads
- [security] Tool “get_provider_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_token_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_workload_cost” rewrote its description, which is the text the model reads
- [functional] Server version: 1.17.0 → 1.19.0

### 2026-10-30 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [security] Tool “get_gpu_market_prices” rewrote its description, which is the text the model reads
- [functional] Server version: 1.16.1 → 1.17.0

### 2026-10-29 (score 74, 0)

- [security regression] Tool “estimate_gpu_cost” was removed
- [security regression] Tool “estimate_token_cost” was removed
- [security regression] Tool “find_gpu_for_model” was removed
- [security regression] Tool “get_forward_curve” was removed
- [security regression] Tool “get_gpu_volume_metrics” was removed
- [security regression] Tool “get_market_overview” was removed
- [security regression] Tool “get_market_stats” was removed
- [security regression] Tool “get_token_volume” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [security] Tool “get_data_status” rewrote its description, which is the text the model reads
- [security] Tool “get_gpu_market_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_gpu_price_at” rewrote its description, which is the text the model reads
- [security] Tool “get_gpu_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_model_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_price_changes” rewrote its description, which is the text the model reads
- [security] Tool “get_provider_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_token_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_workload_cost” rewrote its description, which is the text the model reads
- [security] Tool “list_indices” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 108 → 159
- [functional regression] Resource “gpu-index-latest” was removed
- [functional regression] Resource “manifests” was removed
- [functional regression] Resource “token-index-latest” was removed
- [functional] Server version: 1.12.0 → 1.16.1
- [cosmetic] “get_model_prices” added an optional parameter “every”
- [cosmetic] “fetch” reworded the description of “id”
- [cosmetic] “get_model_prices” reworded the description of “model”
- [cosmetic] “get_price_changes” reworded the description of “days”
- [cosmetic] “get_workload_cost” reworded the description of “company”
- [cosmetic] “get_workload_cost” reworded the description of “model”
- [cosmetic] “get_gpu_market_prices” dropped the optional parameter “days”
- [cosmetic] Tool “get_workload_cost” changed its title: Inference economics per GPU → Break-even throughput and gross margin
- [cosmetic] Tool “list_indices” changed its title: Every GPU and company covered → Every GPU and company listed

### 2026-10-28 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_gpu_market_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_gpu_prices” rewrote its description, which is the text the model reads
- [functional] Server version: 1.9.0 → 1.12.0
- [cosmetic] “get_gpu_market_prices” reworded the description of “gpu”

### 2026-10-27 (score 74, +4)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_gpu_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_token_prices” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 196 → 106
- [functional improvement] Tool “get_gpu_prices” now declares an output schema
- [functional improvement] Tool “get_price_history” now declares an output schema
- [functional improvement] Tool “get_token_prices” now declares an output schema
- [functional] The server now declares the “prompts” capability
- [functional] The server now declares the “resources” capability
- [functional] First check of Capabilities: pass
- [functional] First check of Schema quality: 100
- [functional] First check of Tool coverage: 100
- [functional] New prompt “check_a_price”
- [functional] New prompt “gpu_price_brief”
- [functional] New prompt “token_price_comparison”
- [functional] New resource “compute-screener-view”
- [functional] New resource “gpu-index-latest”
- [functional] New resource “manifests”
- [functional] New resource “site-guide”
- [functional] New resource “token-index-latest”
- [functional] Server version: 1.5.0 → 1.9.0
- [functional] New tool “estimate_gpu_cost”
- [functional] New tool “estimate_token_cost”
- [functional] New tool “fetch”
- [functional] New tool “find_gpu_for_model”
- [functional] New tool “get_data_status”
- [functional] New tool “get_forward_curve”
- [functional] New tool “get_gpu_market_prices”
- [functional] New tool “get_gpu_price_at”
- [functional] New tool “get_gpu_volume_metrics”
- [functional] New tool “get_market_overview”
- [functional] New tool “get_market_stats”
- [functional] New tool “get_model_prices”
- [functional] New tool “get_price_changes”
- [functional] New tool “get_provider_prices”
- [functional] New tool “get_token_volume”
- [functional] New tool “get_workload_cost”
- [functional] New tool “list_indices”
- [functional] New tool “search”
- [functional] New tool “verify_price”

## MCP tools (14)

### `get_gpu_prices` (~262 tokens)

GPU rental 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 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, read within the last 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".

Input parameters:

- `gpu` (string): One GPU; omit for all listed GPUs.

Output parameters:

- `gpus` (array|null)
- `license` (string|null)
- `markets_note` (string|null): What the compute futures prices are, with markets
- `methodology` (string|null)
- `sources` (string|null)
- `tickers_note` (string|null)
- `unit` (string|null)
- `updated` (string|null): When the GPU prices were last calculated (ISO 8601, UTC)

### `get_token_prices` (~156 tokens)

AI 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?".

Input parameters:

- `company` (string): One company; omit for all listed companies.

Output parameters:

- `companies` (array|null)
- `license` (string|null)
- `methodology` (string|null)
- `sources` (string|null)
- `tickers_note` (string|null)
- `unit` (string|null)
- `updated` (string|null): When the token prices were last calculated (ISO 8601, UTC)

### `get_price_history` (~202 tokens)

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).

Input parameters:

- `days` (integer): How many days back from the latest value.
- `from` (string): First day of a period, YYYY-MM-DD (instead of days).
- `name` (string, required): A GPU or an AI company.
- `to` (string): Last day of the period, YYYY-MM-DD; omit for the latest.

Output parameters:

- `kind` (string|null)
- `license` (string|null)
- `name` (string|null)
- `note` (string|null): With from: how the period's values are dated
- `points` (array|null)
- `sources` (string|null)
- `unit` (string|null)
- `url` (string|null)

### `get_model_prices` (~445 tokens)

AI model API 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 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 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".

Input parameters:

- `company` (string): List only this company's models: one of the token index's companies (Anthropic, OpenAI, Google, xAI, Meta, Moonshot AI, Alibaba, DeepSeek, Z.ai, Xiaomi, StepFun, MiniMax, Mistral, Reflection AI, NVID…
- `every` (boolean): List every model on the Every AI model page (/models), not only those with a page.
- `limit` (integer): How many models to list (the Every AI model page lists over 300).
- `model` (string): A model's name, page id or OpenRouter id; omit to list models.
- `sort` (string): "price": the cheapest at the mix first (every model's default); "name": by company and name. A company's models otherwise come by usage, as its page lists them.

Output parameters:

- `fields` (string|null): What each figure of a model's row is
- `license` (string|null)
- `models` (array|null)
- `note` (string|null)
- `sources` (string|null)
- `total` (integer|null): How many models the list has before limit
- `unit` (string|null)
- `updated` (string|null)

### `get_provider_prices` (~180 tokens)

GPU prices by provider

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".

Input parameters:

- `gpu` (string): Only this GPU.
- `provider` (string): A provider's name or page id; omit for all providers.

Output parameters:

- `license` (string|null)
- `note` (string|null)
- `other_posted_prices` (array|null): With a GPU: the providers outside the index (the hyperscalers and others), each one's lowest on-demand price per GPU-hour as posted, not standardized, as the GPU's page lists them
- `providers` (array|null)
- `unit` (string|null)
- `updated` (string|null)

### `get_price_changes` (~107 tokens)

What changed

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.

Input parameters:

- `days` (integer): How many days back: 1, 5, 7 or 30.

Output parameters:

- `days` (integer|null)
- `index_moves` (array|null)
- `license` (string|null)
- `model_price_changes` (array|null): Each model whose price at the mix (87% cache read, 12% input, 1% output) moved, as its page's chart and changes show it

### `get_gpu_market_prices` (~263 tokens)

Prices of every other GPU

Rental prices of every other GPU, as the site's Every GPU page lists them (https://computescreener.com/gpus): RTX 5090, A40, L4, GH200, V100 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).

Input parameters:

- `gpu` (string): A GPU model, e.g. "RTX 5090" or "A40"; omit for all.

Output parameters:

- `about` (string|null)
- `gpus` (array|null)
- `license` (string|null)
- `unit` (string|null)
- `updated` (string|null)

### `get_gpu_price_at` (~125 tokens)

GPU price at a time

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 minutes), else the daily value of that US Central day.

Input parameters:

- `at` (string, required): A date (2026-10-20) or an ISO time (2026-10-26T15:00:00Z).
- `gpu` (string, required): The GPU.

Output parameters:

- `as_of` (string|null)
- `gpu` (string|null)
- `kind` (string|null)
- `note` (string|null)
- `price` (number|null)
- `provisional` (boolean|null)
- `requested` (string|null)
- `unit` (string|null)
- `url` (string|null)

### `get_workload_cost` (~207 tokens)

Break-even throughput and gross margin

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?".

Input parameters:

- `company` (string): Only this company's models.
- `gpu` (string): One GPU; omit for all listed.
- `model` (string): A model's name or page id (e.g. "Claude Opus 5.5"); omit for every model.
- `throughput_tokens_per_second` (number): Tokens per second one GPU generates (input and output, 3 to 1).

Output parameters:

- `license` (string|null)
- `methodology` (string|null)
- `note` (string|null)
- `rows` (array|null)
- `throughput_tokens_per_second` (number|null)

### `list_indices` (~101 tokens)

Every GPU and company listed

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.

Output parameters:

- `companies` (array|null)
- `gpus` (array|null)
- `license` (string|null)
- `methodology` (string|null)
- `other_gpus` (array|null): The GPUs on the Every GPU page, priced as posted by get_gpu_market_prices (not indices)
- `units` (object|null)

### `verify_price` (~123 tokens)

Check a published 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.

Input parameters:

- `date` (string): The index day, YYYY-MM-DD (US Central for GPUs, UTC for companies).
- `name` (string, required): A GPU or an AI company.

Output parameters:

- `date` (string|null)
- `explanation` (string|null)
- `kind` (string|null)
- `manifest` (object|null)
- `methodology` (string|null)
- `name` (string|null)
- `published` (number|null): The value as published for that day
- `recompute` (object|null)
- `status` (string|null): verifiable: final, with a manifest; provisional: the day is not over; pending: final, its manifest comes with the next update; rebuilt_history: before manifests began; restated: final, as recomputed…
- `unit` (string|null)

### `get_data_status` (~67 tokens)

Data freshness and sources

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.

Output parameters:

- `gpu_index` (object|null)
- `manifests` (object|null)
- `methodology` (string|null)
- `token_index` (object|null)
- `verifier` (string|null)

### `search` (~61 tokens)

Search Compute Screener

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.

Input parameters:

- `query` (string, required): Keywords.

Output parameters:

- `results` (array|null)

### `fetch` (~114 tokens)

Read a Compute Screener page

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.

Input parameters:

- `id` (string, required): An id from search, or a page's address (https://computescreener.com/gpu/h100).

Output parameters:

- `id` (string|null)
- `metadata` (object|null)
- `text` (string|null)
- `title` (string|null)
- `url` (string|null)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-computescreener-compute-screener/computescreener#diagnostics

## Score history

- 2026-11-05: 77
- 2026-11-04: 76
- 2026-11-03: 76
- 2026-11-02: 75
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 74
- 2026-10-29: 74
- 2026-10-28: 74
- 2026-10-27: 74
- 2026-10-26: 70
- 2026-10-25: 69
- 2026-10-24: 69

## Common questions

### What is the Compute Screener MCP server?

Compute Screener is an MCP server listed in the public MCP registry as com.computescreener/compute-screener. GPU cloud pricing (H100, H200, B200 per hour) and AI model API pricing per 1M tokens, with history. This page covers its hosted endpoint (https://computescreener.com/mcp).

### Is the Compute Screener MCP server safe to use?

Compute Screener scores 77 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 Compute Screener MCP server expose?

Compute Screener exposes 14 tools: get_gpu_prices, get_token_prices, get_price_history, get_model_prices, get_provider_prices, and 9 more. Their descriptions and schemas cost roughly 2,413 tokens of context every time the server is loaded.

### Does the Compute Screener MCP server require authentication?

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

### Is the Compute Screener MCP server still maintained?

Compute Screener 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.

## Links

- Remote endpoint: https://computescreener.com/mcp
- Website: https://computescreener.com/connect
- Changelog RSS feed: https://verifymcp.io/servers/com-computescreener-compute-screener/computescreener.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-computescreener-compute-screener/computescreener.json
- HTML version of this page: https://verifymcp.io/servers/com-computescreener-compute-screener/computescreener