Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@seo-toolkit-mcp Analyze the meta tags on https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SEO toolkit as an MCP server. Analyze meta tags, robots.txt, sitemaps, keyword density, readability, and heading structure from any AI assistant that supports MCP.
Add to your MCP client config (Claude, Cursor, etc.):
{
"mcpServers": {
"seo-toolkit-mcp": {
"command": "npx",
"args": ["-y", "seo-toolkit-mcp"]
}
}
}Related MCP server: mcp-seo
Tool | Description |
| Analyze a page's SEO meta tags (title, description, OG, Twitter, canonical) |
| Parse robots.txt rules, sitemaps, and crawl directives |
| Validate sitemap.xml format, URL count, and common issues |
| Keyword frequency analysis with single words, bigrams, and trigrams |
| Flesch-Kincaid readability scoring with actionable tips |
| Heading hierarchy (H1-H6) analysis with structure validation |
"Analyze the meta tags on https://example.com"
"Check the robots.txt for example.com"
"Validate the sitemap at https://example.com/sitemap.xml"
"What's the keyword density of this text for 'machine learning'?"
"Score this blog post for readability"
"Check the heading structure of https://example.com/blog/post"
The URL-fetching tools only fetch public web addresses (localhost, private-network and link-local addresses are refused, including through redirects); to analyze a site running on your own machine during local development, set the environment variable SEO_TOOLKIT_ALLOW_PRIVATE=1 in the server's env block.
MIT
Analyze a page's heading hierarchy (H1-H6). Returns the heading outline/tree, counts per level, and issues like missing H1, multiple H1s, or skipped levels. Use to verify content structure for SEO and accessibility.
Inputs: url (required).
Analyze text for keyword frequency and density. Returns top single words, bigrams, and trigrams with percentages. Optionally check density of a specific target keyword. Use to optimize content for target keywords.
Inputs: text (required), target_keyword.
Fetch a URL and analyze its SEO meta tags. Returns title (with length check), meta description, Open Graph tags, Twitter Card tags, canonical URL, and actionable issues. Use this to audit any page's on-page SEO.
Inputs: url (required).
Score text readability using Flesch-Kincaid metrics. Returns Flesch Reading Ease score, grade level, word/sentence/syllable counts, average sentence length, reading time, and actionable tips. Use to ensure content matches your target audience.
Inputs: text (required).
Fetch and parse a site's robots.txt. Returns user-agent rules, allowed/disallowed paths, sitemap directives, crawl-delay, and issues. Use this to check what search engines can/cannot crawl.
Inputs: url (required).
Validate a sitemap.xml file. Returns URL count, format (XML/index/text), sample URLs, last modified dates, and issues like duplicates or missing lastmod. Pass a domain to check /sitemap.xml, or a direct sitemap URL.
Inputs: url (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool targets a distinct aspect of SEO: meta tags, robots.txt, sitemap, keyword analysis, readability, and heading structure. While keyword_density and readability both analyze text, they answer different questions (keyword frequency vs. reading level), so there is minimal risk of confusion.
The names mostly follow a noun-based pattern with snake_case (meta_tags, robots_txt, keyword_density, readability, heading_structure), but sitemap_check breaks the pattern by using a verb prefix. This is a minor inconsistency in an otherwise clear and predictable set.
With 6 tools, the set is well-scoped and each tool provides a distinct function. It's within the ideal 3-15 range and doesn't feel bloated or sparse.
The toolkit covers meta tags, technical SEO files, heading structure, and text-based content analysis. However, there is a notable gap: keyword_density and readability require raw text input, but no tool fetches a page's body content, so agents must rely on external sources to analyze on-page text. Missing features like schema markup analysis are less critical but represent additional gaps.
SEO MCP server for keyword research, live SERPs, backlinks, site audits and AI visibility.
SEO MCP server for keyword research, SERP analysis, audits, and Search Console workflows.
Free MCP server that audits any public URL: technical SEO, Core Web Vitals, indexing checks.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
