Skip to main content
Glama
README.md
# OpenGEO

Open-source MCP server for AI search visibility (GEO / AEO). Give your AI agent real tools to audit and improve how your site shows up inside ChatGPT, Perplexity, Gemini and AI Overviews.

Free and open source. No subscription, no data warehouse account required.

## Why

SEO tooling is crowded. AI search tooling is not. OpenGEO focuses only on the layer the old suites ignore: can AI engines crawl you, cite you, and represent your brand.

## Install

```bash
npx opengeo-mcp
```

### Connect from Claude Desktop / Codex / any MCP client

```json
{
  "mcpServers": {
    "opengeo": {
      "command": "npx",
      "args": ["-y", "opengeo-mcp"]
    }
  }
}
```

## Tools

- `audit_ai_crawlers` - audits a site's robots.txt against 17 major AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Applebot-Extended, Bytespider and more), checks for llms.txt, and returns a 0-100 AI visibility score with per-crawler verdicts.
- `list_ai_crawlers` - lists every AI crawler OpenGEO knows about and what each one does.

## Roadmap

- [ ] **Brand visibility checker** - run a fan-out query set against ChatGPT / Perplexity / AI Overviews and report whether your brand is mentioned and how.
- [ ] **AEO schema audit** - FAQ, speakable, authorship and entity markup checks for answer engines.
- [ ] **Citation tracking** - which of your URLs actually get cited in AI answers, and how that moves over time.
- [ ] **FanoutQ integration** - use [FanoutQ](https://fanoutq.com) as the query-expansion engine behind the brand visibility checker.

## Contributing

PRs welcome. The core logic lives in `src/lib.ts` and is framework-free, so you can reuse it in CLIs and tests.

## License

MIT. An open-source project from the [FanoutQ](https://fanoutq.com) team.

TDQS

A3.7/5.0

Scored across 2 tools

Disambiguation5/5

audit_ai_crawlers performs an active site analysis, while list_ai_crawlers is a static reference enumeration of known user agents. The verbs and objects are distinct, and the descriptions reinforce the separation with no realistic chance of misselection.

Naming Consistency5/5

Both tools follow the same snake_case verb_noun pattern (audit_/list_ + ai_crawlers), sharing the same domain object. Fully predictable and consistent.

Tool Count2/5

Two tools is very thin for a server named OpenGEO, which implies generative-engine-optimization work well beyond a single crawler-access check. Only one functional tool plus one lookup helper leaves most of the apparent scope unaddressed.

Completeness3/5

The audit covers robots.txt verdicts, llms.txt presence, and a score, which is a coherent core, but there is no path to remediation (generating robots.txt rules or llms.txt), no inspection of llms.txt or sitemap contents, and no page-level content audit. Agents hit a dead end after diagnosis.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues