GEO Optimizer

A CLI, Python library and MCP server that scores how ready a site is to be cited by ChatGPT, Perplexity and AI Overviews

CLIMedium risk

auriti-labs/geo-optimizer-skill

Install

pip install geo-optimizer-skill
geo audit --url https://yoursite.com

Without installing: uvx --from geo-optimizer-skill geo audit --url https://yoursite.com.

This is third-party code. Review the repository files before installing.

What it does

geo audit scores a site from 0 to 100 across eight categories and returns prioritized fixes. It checks AI bot access in robots.txt, llms.txt presence and depth, JSON-LD markup, brand entity coherence and content citability using methods from the Princeton KDD 2024 and AutoGEO research. It generates llms.txt and JSON-LD, compares sites, and geo citations asks answer engines typical questions to see whether the brand is cited. The same is available to agents through the geo-mcp MCP server, and the repository includes a SKILL.md with the workflow.

Who it is for. For SEO specialists and site developers who care about appearing in AI search answers.

Good fit when

  • You need to find out why AI engines do not cite your site
  • You need to generate llms.txt and JSON-LD markup
  • You want an AI search readiness check in CI

Not a fit when

  • You need classic rank tracking
  • The site is not publicly reachable

Example request

Check how ready my site is to be cited by ChatGPT and fix what is missing

Limitations

Methods and bot lists target Western AI search engines. Citation checks and LLM analysis need model provider keys. Monitoring and score history are only in the paid GeoReady platform; the CLI stays free under MIT.

How to disable. Remove the package with pip uninstall geo-optimizer-skill and the MCP server with claude mcp remove geo-optimizer.

Security check

  • Crawls site pages and calls external AI services for citation checks

README in short

The README explains how GEO differs from SEO, shows a quick start via pip or uvx and covers the audit, llms.txt and schema commands. It describes a GitHub Action for CI, the MCP server and its tools, context files for Claude Projects, Cursor and Windsurf, a Python API and an Astro integration. A table separates the free CLI from the paid GeoReady platform.

FAQ

Can I run it without installing?

Yes: uvx --from geo-optimizer-skill geo audit --url https://yoursite.com.

How is GEO different from SEO?

SEO is about ranking in results; GEO is about whether an AI engine can read a page and cite it in an answer.

A Claude Code plugin for SEO audits: technical SEO, E-E-A-T, schema, local and AI search via parallel subagents

PluginHigh risk16.9K

A Claude Code skill set for auditing sites for AI search: citability, AI crawler access, llms.txt, schema and reports

SkillMedium risk10.6K

The experimental official Google Analytics 4 MCP server: reports, funnels and realtime data on request

MCP serverMedium risk3.2K

Google Search Console MCP

Google Search Console MCP Server for SEOs

An MCP server for Google Search Console: queries and pages with clicks and positions, URL indexing checks, sitemaps and ready SEO skills

MCP serverMedium risk1.5K