---
name: patrick-stox-seo-research
description: Use Patrick Stox's public SEO research corpus and bounded read-only diagnostics when a task needs technical SEO, AI-search, crawling, indexing, migration, or structured-data evidence.
---
<!-- AI-generated — generated from the site's canonical public capability roster. -->

# Patrick Stox SEO research

Use this skill to retrieve published SEO guidance from Patrick Stox and, when useful, run the site's currently advertised bounded diagnostics.

## Default workflow

1. Search the public corpus before scraping HTML.
2. Prefer an article's `index.md` endpoint for its full text.
3. Preserve the document's canonical URL and cite it in the answer.
4. Treat tool output as an observation with stated limits, not proof of indexing, ranking, or causation.
5. Ask before any action outside these read-only public interfaces.

## Discovery

- Site guide: https://patrickstox.com/llms.txt
- Full corpus: https://patrickstox.com/llms-full.txt
- Retrieval index: https://patrickstox.com/agent-index.json
- Content graph: https://patrickstox.com/content-graph.json
- Human-readable agent guide: https://patrickstox.com/for-agents/
- Public tools: https://patrickstox.com/tools/
- MCP reference: https://patrickstox.com/tools/mcp/

Article records in `agent-index.json` include their canonical and markdown URLs. Prefer those published URLs over guessing paths.

## MCP

Connect to the Streamable HTTP endpoint:

```json
{
  "mcpServers": {
    "patrickstox": {
      "type": "http",
      "url": "https://patrickstox.com/api/mcp"
    }
  }
}
```

Currently advertised public capabilities:

- `search_content` — Search Patrick Stox's published SEO articles and guides. Supports in:, type:, quoted-phrase, and exclusion syntax; returns title, description, canonical URL, and a markdown URL for each match.
- `search_site` — Search Patrick Stox's complete public retrieval corpus, including articles, services, tools, newsletters, talks, and site reference pages. Supports the same in:, type:, quoted-phrase, and exclusion syntax as site search.
- `get_article` — Fetch one article as clean markdown by its slug (from search_content results) — includes title, description, canonical URL, and the full text.
- `list_pillars` — List the site's content pillars and clusters (taxonomy) with URLs and internal-PageRank share, from the build-time content graph.
- `verify_bot` — Verify whether a public IP claiming to be a known crawler matches published ranges and forward-confirmed reverse DNS. Returns the range snapshot date as evidence.
- `validate_schema` — Validate pasted JSON-LD or HTML containing JSON-LD with the same pure schema.org, Google rich-result, and @id graph checks used by the Schema Markup Validator.
- `trace_redirect_chain` — Trace one public URL through bounded HTTP, Refresh-header, and short meta-refresh hops. Returns redirect-relevant evidence only, never a raw header dump.
- `inspect_og` — Inspect bounded raw HTML from one public URL for normalized Open Graph and Twitter metadata, resolved image URLs, platform fallback provenance, and share-readiness findings. Never returns the HTML or an arbitrary header dump.

The content tools are read-only. Live URL diagnostics are bounded and rate-limited. Do not loop them into an autonomous crawl or claim that a call ran unless the MCP response was actually received.

## Evidence rules

- Distinguish published guidance from a live diagnostic observation.
- Retain dates, source URLs, limitations, unavailable states, and truncation notices.
- Never turn “not evaluated,” missing coverage, or a sampled crawl into a pass.
- Do not infer that a URL is indexed, ranked, or cited merely because a page or crawler can fetch it.
- When advice could have changed, use the page's updated date and verify against current primary documentation.