MCP server · Analytics
SEO Tools MCP servers
by antohins
Lets your AI pull SEO data from Google, Yandex and A-Parser: rankings, search volume, traffic and site health.
This is a set of small helper programs that connect your AI assistant to popular SEO data sources: Google Search Console, Google Analytics 4, Yandex Wordstat, Yandex.Webmaster, Yandex.Metrica, plus paid SERP services and your own A-Parser setup. It is handy if you do SEO for the Russian or global market and want to ask questions in plain chat instead of clicking through five different dashboards. Everything is read-only, so it looks things up but never changes anything in your accounts.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill, in this case a connection to SEO tools and services like Google Search Console or Yandex Wordstat. Once it is connected, your AI can go and look things up there when you ask. This project actually bundles eight of these helpers, one per service, and you only turn on the ones you need.
What this MCP server does
You ask your AI a question in normal words, for example how many clicks a page got last month. The AI picks the right helper for that service and sends your request through it. The helper talks to the service using your own login or key, then brings the answer back. Your AI reads the result and explains it to you in the chat, or turns it into a table or a short summary. Nothing gets published or changed on your side, it only reads.
Click to zoomWhat you can do with it
- Check where your site ranks in Google or Yandex for a keyword
- See how often people search a phrase in Yandex Wordstat
- Pull clicks, impressions and average position from Google Search Console
- Look at traffic, sources and top pages in Google Analytics 4 or Yandex.Metrica
- Check whether a page is indexed and find broken links in Yandex.Webmaster
- Get search suggestions and People Also Ask questions for a topic
- Run searches through your own A-Parser instance
Try asking your AI
- “How many clicks and impressions did my site get in Google Search Console over the last 28 days?”
- “Show me the monthly search volume in Yandex Wordstat for the phrase buy running shoes”
- “Which pages brought the most organic traffic in Google Analytics last month?”
- “Check whether this URL is indexed in Google and Yandex”
What it gives back to you
You get answers in the chat: numbers, lists and short summaries, often as a small table. For example a list of keywords with their search volume, or a table of pages with clicks and average position. Some tools return details like indexing status, sitemap status, or a list of broken links. The AI can also explain what the numbers mean if you ask.
Before you start
What you need
- The Claude desktop app or Claude Code
- An account and API key for the paid services you want to use, like XMLStock or XMLRiver (the site gives you a key after you sign up)
- Access to the Google or Yandex properties you want to read, such as a Search Console site or a Metrica counter
- For A-Parser: your own running A-Parser instance with its URL and API password
Good to know
Some tools call paid services and spend money or proxy traffic each time they run, so check costs before asking for large batches.
Install it with your AI
Add SEO Tools MCP servers to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check SEO Tools MCP servers, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
SEO specialists, content and marketing people, and site owners who work with Google and Yandex data and prefer asking questions in chat over clicking through dashboards.
