SE Ranking runs a remote server that exposes both SEO and project data via one API. The endpoint is api.seranking.com/mcp over Streamable HTTP, with OAuth.
https://api.seranking.com/mcp
Claude Sonnet 4.5
Chat with 60+ AI models on the same workflow — switch to a different model mid-conversation and re-run the same prompt, or use Compare mode to put several side-by-side and balance quality vs. cost.
OAuth against your SE Ranking account. Calls draw on the API credits in your plan.
How models use it and what it is built for.
Tools it exposes: backlinks, domain analysis, keyword research and website audit on the data side, plus on the project side you get project and keyword management, rank tracking with history, competitor tracking, and a GSC-backed traffic module.
Clients it lists support for: Claude.ai (web), Claude Desktop, Claude Code, Codex (CLI and IDE), Cursor, VS Code, Windsurf, Zed, Gemini CLI and v0 by Vercel.
SE Ranking wraps the MCP into production-ready Claude Skills for content briefs, backlink gap, keyword clusters, competitor gaps, etc. Worth a look if you would rather start from a constrained workflow than write the system prompt that constrains it.
Typical tools an AI model can call. Exact names vary by version.
Copy any of these into MCP Agent Studio after connecting.
Compare backlinks for my domain and this competitor, then list the ten strongest domains linking to them but not to me.
Which of my tracked keywords lost positions in the last 30 days, and what changed in the SERP for them?
Run an audit on this project and give me a top-ten fix list ranked by impact and effort.
Where does my brand appear in AI Overviews and ChatGPT answers for our five core keywords?
This is not a single-model product: you get the same MCP connection with 60+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.
Default pick for SE Ranking
Claude Sonnet 4.5
Most questions here join project history to market data before drawing a conclusion. Sonnet 4.5 holds both sides in view; cheaper models report one and ignore the other.
Listing tools proves the server is reachable, not that a model can work with it. Evals go further: they read every tool on the server, write a test suite from its real schemas, and run it — code decides pass/fail on the responses (schema conformance, error codes, pagination, result caps) while a scoring model grades plain-English tasks driven through the tools.
Get a pass/fail report per tool with the evidence behind each verdict — and replay the same suite after every schema change. Destructive tools are excluded from the run.
Run evalsOpen MCP Agent Studio with the connection pre-filled. Add your token, pick any of 60+ models, and start chatting — no install required.
Open Agent StudioCommon questions about connecting, scoping and using it safely.
SE Ranking’s hosted MCP server at api.seranking.com/mcp. It exposes more than 180 SEO and GEO tools — keyword research, domain analysis, backlinks, website audits, rank tracking and AI search visibility — to any MCP client over streamable HTTP with OAuth.
No. MCP access is included in every SE Ranking subscription rather than billed as an add-on, and it runs on the API credits already in your plan. If you want MCP without a subscription, there is a pay-as-you-go API plan starting at $50 for 250,000 credits with no expiry.
Those two answer questions about a market. SE Ranking does that as well, but it also reaches your own projects — tracked keywords, ranking history, audits and a Search Console-backed traffic module — so an agent can reason about the domains you already monitor.
Any MCP client that speaks streamable HTTP. SE Ranking lists Claude on the web, Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Codex, Zed and Gemini CLI among the tested ones. Nothing is installed locally — you paste the URL and authorise.
SE Ranking publishes open-source Claude Skills built on the server — content briefs, backlink gap, keyword clusters, competitor gaps, technical audit. Each one turns the raw tools into a structured deliverable, which is a faster start than writing the system prompt that constrains them yourself.
Semrush
Pull keyword, domain and competitor data into an agent instead of exporting CSVs.
Ahrefs
Backlink and ranking data an agent can query directly, without the export step.
DataForSEO
Raw SERP, keyword and backlink APIs priced per call, for agents that assemble their own analysis.
OpenSEO
Keyword research, SERP data, rank tracking and Search Console metrics, from chat.