# geo-score

> MIT free AIV readiness score + MCP — cite-ability without a paywall

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://github.com/jianruntech/geo-score  
**GitHub:** https://github.com/jianruntech/geo-score  
**Added:** 2026-10-04

---

## The Hook

geo-score answers “can AI engines cite this site?” with a free 0–100 readiness score from one command — then optional Ask/Watch tiers that spend only the provider keys you bring.

## What's Good

MIT (jianruntech/geo-score). PyPI `geo-score` v1.6.0 (HTTP 200). Score path is stdlib Python, no API key, no install required for the raw CLI; MCP via `uvx geo-score@1.6.0 mcp` (score free; `--read-only` for spend-safe). Claude Code skill + open rubric v1.1. Leaderboard at jianruntech.com. ★~619.

## The Catch

Spend: `ask` and `run`/`Watch` call AI engines with YOUR keys — Score is free, citation checks are not. Vs firecrawl / open-seo-class hosted SEO tools: Firecrawl is crawl→markdown; open-seo leans on a hosted path — geo-score’s catch is an open AIV readiness rubric + local MCP with a zero-key Score tier. Rubric is readiness, not a guarantee engines will cite you.

## Verdict

MIT GEO/AIV score+MCP when you need a free cite-ability bar before paying for Ask/Watch — not Firecrawl crawl; bring keys only for engine asks.