Skip to content
AI Compute Radar logo

AI Compute Radar MCP server

Which MCP servers are AI Compute Radar'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 2026-10-21

← Back to AI Compute Radar

Whose server it is
  • Registry namedev.aicomputeradar/ai-compute-radarverified in the MCP registry

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

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools5
  • Server calls itselfai-compute-radar
  • Server version1.2.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 380 ms.

Should an agent connect itConnect it
  • Its tools do every use case we checked: check which open AI models fit a given GPU; compare hourly rental prices for cloud GPUs.

Once connected

  • For "check which open AI models fit a given GPU", the likely first call is find_fit.
  • For "compare hourly rental prices for cloud GPUs", the likely first call is gpu_prices.

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: 7, the first on 2026-10-21
  • INITE MCP score96 of 100answers 100 · does the job 100 · definitions 83 · context 100 · connects 100
  • What an agent can do with it2 of 2 use cases
  • Answered100% of days7 of 7 daily checks
  • Median first answer259 ms
  • Space in an agent's context≈ 833 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 5 of 5

What an agent can do with it

  • can do · check which open AI models fit a given GPU
  • can do · compare hourly rental prices for cloud GPUs
  • not sure · track which open AI models are gaining downloads

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 offers5 tools · read 2026-10-21
  • trending_models

    Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have…

  • find_fit

    Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict…

  • gpu_prices

    Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week…

  • list_hardware

    Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.

  • weekly_pick

    The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a…

How to connect

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

{
  "mcpServers": {
    "ai-compute-radar": {
      "type": "http",
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http aicomputeradar https://aicomputeradar.dev/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://aicomputeradar.dev/api/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.