Audit titles, descriptions, headings, canonical tags and JSON-LD syntax with the local, read-only MCP SEO Auditor.
MCP SEO Auditor performs static HTML checks through three read-only tools. It can inspect supplied HTML, fetch a page for an audit or crawl a small set of pages to find basic metadata and markup problems.
Check the title, meta description, H1, canonical, robots directive and relevant image alt text. Review each finding against the page’s intended purpose. The JSON-LD check concerns syntax; passing it does not establish rich-result eligibility or a search ranking.
The documented MVP requires Python 3.11 or later, with a Node wrapper launched through npx -y mcp-seo-auditor. crawl_site accepts one to ten pages and defaults to five. Audits inspect static HTML rather than rendering client-side JavaScript, so a browser check remains useful when content appears only after scripts run.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| audit_html | Audit supplied static HTML. |
| audit_url | Fetch and audit a URL. |
| crawl_site | Audit a small crawl of one to ten pages. |
{
"mcpServers": {
"seo-auditor": {
"command": "npx",
"args": [
"-y",
"mcp-seo-auditor"
]
}
}
}Node.js with npx and Python 3.11+ on PATH, or an absolute Python executable set in MCP_SEO_PYTHON.
| Variable | Description | Required |
|---|---|---|
| MCP_SEO_PYTHON | Optional absolute path to Python 3.11 or later. | Optional |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.