I connected Claude to my SEO data. Here's the setup, and what to ask it

Every SEO tool I've used has the same workflow. Open the dashboard, find the chart that moved, export it, paste it into a chat window, then ask the AI what it means. The AI is good at the "what it means" part. The copying is the job nobody signed up for.

MCP (Model Context Protocol) removes the copying. It's an open standard that lets an assistant like Claude or ChatGPT call tools on a server you've connected, so it can read your data itself instead of waiting for you to paste it.

I build Ranklogs, an SEO platform, so full disclosure: this walkthrough uses our MCP server. The setup steps work the same way for any remote MCP server with sign-in.

What you need

• A Ranklogs account. The 14-day trial works and needs no card.
• One of these: the Claude app (desktop or claude.ai), Claude Code, ChatGPT with developer mode, or Cursor.
• The server URL: https://mcp.ranklogs.com/mcp

Connect it to the Claude app

1. Open Settings → Customize → Connectors, click + Add, then Add custom connector.
2. Give it a name (Ranklogs) and paste the server URL. Click Continue.
3. Claude detects that the server uses sign-in and registers itself automatically. You don't need to create API keys.
4. A Ranklogs sign-in page opens. Log in, then choose the access level on the consent screen. Read only is pre-selected.
5. Back in Claude, the connector lists its tools. Start a new chat and it's ready.

The whole thing takes about two minutes.

Connect it to Claude Code

One command in your terminal:

claude mcp add --transport http ranklogs https://mcp.ranklogs.com/mcp

Then start Claude Code, type /mcp, pick ranklogs and sign in through the browser window it opens.

This is the setup I use most. Claude Code can read what's wrong from your SEO data and then fix it in the repo: add the missing meta description, the schema, the internal link. It shows each change before saving it.

Connect it to ChatGPT or Cursor

ChatGPT: turn on developer mode under Settings → Connectors → Advanced → Developer mode, add a connector pointing at the server URL and sign in when asked. Without developer mode, ChatGPT only exposes generic search and fetch, so you won't see the named tools.

Cursor: Settings → MCP Tools → Add new MCP server, paste the URL and sign in.

What to ask it

The server has 27 tools. You never call them by name; you ask in plain English and the assistant picks. Here's what's worked for me, with the tools it ends up calling:

"Which of my keywords dropped this week, and why?"
It calls get_ranking_alerts, then get_audit_issues on the page that dropped. The useful part is the second call: a drop next to a fresh audit issue on the same page is usually the answer.

"What should I fix first on my site?"
get_project_overview plus get_audit_issues. You get a short list ordered by impact, not 400 warnings sorted by severity.

"Does ChatGPT cite us for our main questions? If not, who does it cite instead?"
get_ai_visibility and get_ai_citations. This is the one I'd start with if you've never looked. Most sites are surprised by who gets cited in their place.

"Find keywords my competitor ranks for that I don't, and pick the one I can actually win."
get_keyword_battleground, then research_keywords to check volume and difficulty on the shortlist.

"Write the JSON-LD for this FAQ page."
generate_schema. Paste the questions and answers; it returns valid markup.

What it can and can't do

• It reads your account, nothing else. You connect with your own login, and the connection only sees your projects. You can revoke it any time under Profile → Connected AI apps.
• Read-only unless you say otherwise. 23 of the 27 tools only read. The other 4 can act: add keywords to a project, add an AI-visibility prompt, generate a content brief, and run a gap analysis on an AI prompt you're missing from. They only work if you chose Read and write on the consent screen.
• Asking about existing data is free. Rankings, audits and AI visibility you're already tracking cost nothing to query. Fresh research, like new keyword ideas, uses your plan's monthly lookups.
• It doesn't publish anything to your site. In the Claude app it drafts. In Claude Code it edits files in your repo and shows you the change first.
• It's only as fresh as the last check. Rankings are checked daily for the top 50 positions and weekly for 51 to 100.

Why bother

The point isn't that an AI can read a chart. It's that the question you actually have ("what changed, why, what do I do") is answered by combining three or four reports, and that combining is exactly the busywork nobody wants. Connect the data once and you ask the question directly.

Setup guide with screenshots: ranklogs.com/mcp