Connect AI Compute Radar and your agent gets 6 tools, among them find_fit, gpu_prices, list_hardware. It answers at https://aicomputeradar.dev/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 6 November 2026, succeeded.
Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED Inputs: hardware, model, context, kv |
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 collected |
list_hardware | Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit. |
price_history | Daily price history per GPU class and source, up to 90 days: the rows the Rent Index and the 30-day range are computed from. Marketplace days (Vast.ai, Clore.ai) are medians over the day's counted hourly medians with min, p75 and offer coun Inputs: gpu, source, days |
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 heat= Inputs: limit, slug |
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 device-by-device Inputs: week |
Every block below points at https://aicomputeradar.dev/api/mcp. Pick your client and copy.
claude mcp add --transport http ai-compute-radar https://aicomputeradar.dev/api/mcp
{
"mcpServers": {
"ai-compute-radar": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://aicomputeradar.dev/api/mcp"]
}
}
}{
"mcpServers": {
"ai-compute-radar": {
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}{
"servers": {
"ai-compute-radar": {
"type": "http",
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}{
"context_servers": {
"ai-compute-radar": {
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}{
"mcpServers": {
"ai-compute-radar": {
"serverUrl": "https://aicomputeradar.dev/api/mcp"
}
}
}{
"mcpServers": {
"ai-compute-radar": {
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}name: AI Compute Radar
version: 0.0.1
schema: v1
mcpServers:
- name: AI Compute Radar
type: streamable-http
url: https://aicomputeradar.dev/api/mcp{
"mcpServers": {
"ai-compute-radar": {
"httpUrl": "https://aicomputeradar.dev/api/mcp"
}
}
}{
"mcpServers": {
"ai-compute-radar": {
"type": "http",
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}{
"mcpServers": {
"ai-compute-radar": {
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Faicomputeradar.dev%2Fapi%2Fmcp&type=streamable_http&id=ai-compute-radar&name=AI%20Compute%20Radar
It answered our last check on 6 November 2026 in 204 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by aicomputeradar.dev and served from aicomputeradar.dev, the vendor's own domain: https://aicomputeradar.dev/api/mcp.
6, as returned by the server's own tools/list on 9 November 2026: find_fit, gpu_prices, list_hardware, price_history, trending_models, weekly_pick.
It answered our last check on 6 November 2026 in 204 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://aicomputeradar.dev/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.aicomputeradar. Endpoint host: aicomputeradar.dev. ARD identifier: urn:air:dev.aicomputeradar:mcp:ai-compute-radar.
First indexed 18 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.