audit_onpage
Audit on-page SEO for a project's latest crawl: titles, meta descriptions, h1s, canonicals, and thin content, per page. Run crawl_site first.
Cost: 30 credits.
audit_onpage reviews the on-page SEO of the pages captured by your project's most recent crawl_site run. It is synchronous: it returns the findings immediately. Run crawl_site first — if the project has never been crawled, the tool tells you so and charges nothing.
What it does
Runs a rule engine over every crawled page and reports, per page, issues such as:
- Titles — missing, too long (over ~60 characters), too short, or duplicated across pages.
- Meta descriptions — missing, too long (over ~160 characters), too short, or duplicated.
- Headings — a missing
h1, or more than oneh1. - Canonicals — missing, or pointing to a different URL than the page itself.
- Thin content — pages under ~200 words.
Thresholds are conservative "worth a look" signals, not hard rules.
Example
Ask your MCP client in plain language:
Run an on-page audit for my example.com project.
Input
| Field | Type | Required | Description |
|---|---|---|---|
project_id | string (uuid) | Yes | The project to audit (from setup_project / list_projects). |
Returns
A summary of issue counts followed by a per-page list of findings. Pages with no issues are counted but not listed.
analyze_content_decay
Find decaying pages from your latest Search Console pull: pages whose clicks dropped meaningfully (absolute and proportional) vs the previous window…
audit_tech
Audit technical SEO for a project's latest crawl: HTTP status spread, redirects, skipped URLs by reason, and robots (noindex) conflicts. Run crawl_site…