AI Compute Radar MCP MCP server

Provides AI agents with read-only access to measured data on open models, GPU hardware compatibility, rental prices, and weekly model picks. It exposes tools for finding fitting models, checking GPU prices, listing hardware, and retrieving the weekly pick, all with provenance metadata.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by AI Compute Radar

MCP endpoint (Streamable HTTP)

https://aicomputeradar.dev/api/mcp

Vendor documentation

What you can do with it

Find models that fit specific hardware constraints
Check current GPU rental median prices
Retrieve the weekly recommended model pick
List available GPU and Mac hardware profiles

Tools advertised by the last live check:

trending_models
find_fit
gpu_prices
list_hardware
weekly_pick

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add ai-compute-radar-mcp --url https://aicomputeradar.dev/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-compute-radar-mcp in your MCP settings.

Cursor configuration

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

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

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-compute-radar-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http ai-compute-radar-mcp https://aicomputeradar.dev/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

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

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "ai-compute-radar-mcp": {
      "serverUrl": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

See all 782

Do you run AI Compute Radar MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing