AI Model Radar MCP server

Connect AI Model Radar and your agent gets 5 tools, among them find_fit, gpu_prices, list_hardware. It answers at https://aimodelradar.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 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.

Status

Answering

Tools

Official

yes, served from aimodelradar.dev

Reliability

6 of 6 checks

Response time

264 ms

Transport

streamable HTTP

Last checked

19 October 2026

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

Description as the publisher wrote it.

The 5 tools AI Model Radar offers

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

Add AI Model Radar to your AI client

Every block below points at https://aimodelradar.dev/api/mcp. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http ai-model-radar https://aimodelradar.dev/api/mcp

Claude Desktop: claude_desktop_config.json

{
  "mcpServers": {
    "ai-model-radar": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://aimodelradar.dev/api/mcp"]
    }
  }
}

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "ai-model-radar": {
      "url": "https://aimodelradar.dev/api/mcp"
    }
  }
}

VS Code and GitHub Copilot: .vscode/mcp.json

{
  "servers": {
    "ai-model-radar": {
      "type": "http",
      "url": "https://aimodelradar.dev/api/mcp"
    }
  }
}

Zed: Zed settings.json

{
  "context_servers": {
    "ai-model-radar": {
      "url": "https://aimodelradar.dev/api/mcp"
    }
  }
}

Windsurf: ~/.codeium/mcp_config.json

{
  "mcpServers": {
    "ai-model-radar": {
      "serverUrl": "https://aimodelradar.dev/api/mcp"
    }
  }
}

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

{
  "mcpServers": {
    "ai-model-radar": {
      "url": "https://aimodelradar.dev/api/mcp"
    }
  }
}

Continue: .continue/mcpServers/neuronto.yaml

name: AI Model Radar
version: 0.0.1
schema: v1
mcpServers:
  - name: AI Model Radar
    type: streamable-http
    url: https://aimodelradar.dev/api/mcp

Gemini CLI: ~/.gemini/settings.json

{
  "mcpServers": {
    "ai-model-radar": {
      "httpUrl": "https://aimodelradar.dev/api/mcp"
    }
  }
}

Codex CLI: MCP server config

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

Warp: MCP servers, + Add, paste JSON

{
  "mcpServers": {
    "ai-model-radar": {
      "url": "https://aimodelradar.dev/api/mcp"
    }
  }
}

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Faimodelradar.dev%2Fapi%2Fmcp&type=streamable_http&id=ai-model-radar&name=AI%20Model%20Radar

Is AI Model Radar up right now?

It answered our last check on 19 October 2026 in 264 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to AI Model Radar

FitLLM3 tools Zhiyong AI Technology Decision Radar11 tools Outfit Assistant3 tools Orbator4 tools AI API Radar4 tools io.github.QBT-Labs/openmm-mcp15 tools

Questions about AI Model Radar

Is there an official AI Model Radar MCP server?

Yes. It is published by aimodelradar.dev and served from aimodelradar.dev, the vendor's own domain: https://aimodelradar.dev/api/mcp.

How many tools does AI Model Radar have?

5, as returned by the server's own tools/list on 11 September 2026: find_fit, gpu_prices, list_hardware, trending_models, weekly_pick.

Is AI Model Radar down?

It answered our last check on 19 October 2026 in 264 ms. Over 6 checks since 10 September 2026 it answered 6.

How do I add AI Model Radar to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://aimodelradar.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.

Does AI Model Radar need an API key?

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.

Where this comes from

Publisher: dev.aimodelradar. Endpoint host: aimodelradar.dev. ARD identifier: urn:air:dev.aimodelradar:mcp:ai-model-radar. First indexed 10 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.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.