SEO MCP servers
4 hosted MCP servers are available in SEO. Open one for its tools and the Claude Code command. Client guides cover ChatGPT and Cursor, and which clients have been tested.
- Live
Site Audit MCP server
Audit, monitor and troubleshoot any public website from one MCP server.
Ask your AI assistant to audit a page before launch, after a redesign, or when a client asks why a link preview looks wrong. Site Audit fetches the page from our servers, reads the served HTML, and returns specific findings with fixes. The same server also watches pages and uptime on a schedule, and checks SSL certificates, redirects, DNS and email records, security headers, sitemaps, robots.txt, accessibility, page weight and the technology a site uses.
Hosted — nothing to install · For: Freelancers, agencies and in-house marketers who check client or company pages every week.
- Live
Google Search Console MCP server
Your real Google queries and pages, next to the audit findings.
Connect your own Google Search Console (read-only) and ask which queries are close to page one, how a page's clicks and position changed, and how that lines up with its Site Audit findings. Data is read from Google when you ask; we do not store it.
Hosted — nothing to install · For: SEO freelancers and site owners doing weekly performance reviews.
- Live
SEO Toolkit MCP server
JSON-LD, social tags, robots files and URL helpers in one MCP server.
Build schema.org JSON-LD (FAQ, LocalBusiness, Organization, HowTo, Product, Article, WebSite, Event, Review, Video, BreadcrumbList), Open Graph and Twitter cards, canonical / robots / hreflang tags, robots.txt, llms.txt, humans.txt, security.txt, ads.txt and a web manifest, plus SERP snippet length, keyword density and URL slug, normalize, encode and punycode helpers. Paste the output — this does not fetch your live pages (Site Audit does that).
Hosted — nothing to install · For: SEO and content teams who paste markup rather than click through a dozen one-off tools.
- Live
Web Research MCP server
Search the web, read pages, and look things up on Wikipedia, Wikidata, Hacker News and RSS feeds.
One research server for the open web. Wikipedia, Wikidata, Hacker News, RSS/Atom feeds, Wikimedia Commons images and public contact details on a website work with no extra key. Add your own Firecrawl API key to also search the web, read any public page as clean text and map a site's URLs; those provider credits are charged through your Firecrawl account.
Hosted — nothing to install · For: Agencies and researchers gathering source material from public websites.
Practical workflows
Follow a step-by-step guide using these servers, with example prompts, source checks and tool limits.
Research NASA image records with AI and MCP
Find indexed space-image records, inspect exact NASA IDs and keep source dates, recorded credits and reuse uncertainty visible in a ToolCargo research workflow.
Find image candidates and inspect their credits with AI and MCP
Use ToolCargo’s Wikimedia Commons MCP to find image candidates, compare dimensions and inspect creator credits and recorded license terms before reuse.
How to run an SEO audit with an AI agent and MCP
Run a repeatable SEO audit with ToolCargo Site Audit: check served HTML, indexing signals and link previews, then verify fixes with your AI agent.
Find keyword opportunities with Google Search Console and MCP
Use Search Console query and page data in your AI agent to prioritize content updates, review CTR and find existing pages near the first page of search.
Monitor SEO changes after launch with an AI agent and MCP
Set up scheduled SEO monitoring with ToolCargo Page Watch: track noindex, canonical and HTTP changes, review alerts, and verify fixes after a website launch.
Find research papers and verify DOI metadata with an AI agent
Build a source-linked research shortlist with ToolCargo Crossref and Wikipedia MCP tools. Check DOI records, preserve missing fields and separate metadata from paper claims.
Find books and compare editions with MCP
Use Open Library MCP tools to find a work, inspect its catalogue record and compare edition dates, publishers, languages and identifiers.
Resolve entities and review Wikidata statements with MCP
Use Wikidata MCP tools to resolve English or Arabic names, inspect an exact entity and review a specific property with ranks, qualifiers and references.