mcpField
A
aiiq-mcp

aiiq-mcp

Local
github.com/shea256AI & Agents0Updated 16w ago
Repository

About aiiq-mcp

aiiq-mcp is a read-only MCP server for querying AI IQ model scores, rankings, benchmarks, capability domains, and methodology. It connects to the public API over HTTPS and requires no API key.

Key features

  1. 01List models and IQ dimension scores
  2. 02Get model details and benchmark results
  3. 03Browse rankings and domain leaderboards
  4. 04Explore benchmark catalog and methodology
  5. 05Compare several models side by side

Use cases

  1. 01Check a model's IQ and scores
  2. 02Compare models for evaluation
  3. 03Review rankings by domain
  4. 04Understand how AI IQ is calculated

MCP support

Exposes read-only AI IQ query tools to MCP clients, including model, ranking, domain, benchmark, and methodology lookups. It accesses the public AI IQ API over HTTPS without an API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "shea256-aiiq": {
      "command": "npx",
      "args": [
        "-y",
        "@aiiq/mcp"
      ],
      "env": {
        "AIIQ_API_BASE": "<AIIQ_API_BASE>"
      }
    }
  }
}
Run commandnpx -y @aiiq/mcp
Environment variables to set
AIIQ_API_BASEOverride the versioned AI IQ API base URL (default https://www.aiiq.org/api/v1).

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@aiiq/mcp0.2.0

Tools

9

Saved tool list · updated 3w ago

This tool takes no parameters.

Details

From the project README

@aiiq/mcp

Model Context Protocol server for AI IQ — query AI model IQ, rankings, applied-capability domains, benchmarks, and methodology from any MCP client (Claude Code, etc.).

Read-only. Talks to the public AI IQ API over HTTPS; no API key required.

Install

Requires Node.js 18+. No API key needed. Works in any MCP client.

Claude Code (one command):

claude mcp add aiiq -- npx -y @aiiq/mcp          # add --scope user for all projects

Claude Desktop — edit claude_desktop_config.json (Settings → Developer → Edit Config) and add:

{
  "mcpServers": {
    "aiiq": { "command": "npx", "args": ["-y", "@aiiq/mcp"] }
  }
}

Then fully quit and reopen the app. (If Node is managed by nvm/asdf, use the absolute path to npx as the command, since the desktop app doesn't inherit your shell PATH.)

Cursor / Windsurf / other clients — same JSON in the client's MCP config:

{ "mcpServers": { "aiiq": { "command": "npx", "args": ["-y", "@aiiq/mcp"] } } }

Tools

  • list_models — all public models with IQ, 7 dimension scores, emotional reasoning, rank, cost
  • get_model — full detail for one model (incl. per-benchmark results)
  • list_rankings — available leaderboards with ids, names, model counts, and URLs
  • get_ranking — ordered models for one ranking id
  • list_domains — applied-capability domains and benchmark counts
  • get_domain — model composite IQs and benchmark leaderboards for one domain
  • list_benchmarks — benchmark catalog
  • get_methodology — how AI IQ is computed
  • compare_models — side-by-side detail for several models

Config

  • AIIQ_API_BASE — override the versioned API base URL (default https://www.aiiq.org/api/v1). A custom value must be the API root that contains paths such as /models and /rankings.

Development

pnpm install
pnpm test
pnpm build

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.