Your data, in context
Read your workspace’s Search Console performance, rankings and crawl results.
MrKeyword runs an MCP server, so Claude can read your workspace directly.
Free plan, free forever · no credit card

Paste one line into Claude Code, the Claude desktop app or Cursor and you can ask about your own Search Console data in plain English — and get an answer with the source attached.

Connect your assistant to the search data you already own. Explore what changed, understand what needs attention, and decide what to do next.
Read your workspace’s Search Console performance, rankings and crawl results.
Follow each figure back to a tool, its source, and the date it describes.
Tokens are read-only by default. You choose the next step and what gets published.
Start with a MrKeyword account and a client that supports MCP. The Free plan is enough to connect.


Open Settings → Connections → API & MCP Tokens. Give your token a label and create it. Leave “Allow this token to make changes” unticked for read-only access.
Copy it somewhere safe. It is shown once.
Use the command below for Claude Code. The Claude SEO MCP setup guide covers Claude Desktop and Cursor step by step, and the SEO MCP server page lists every tool and what it costs.
Your token connects one workspace.
Try “What is hurting my site today?” Your client’s tool list shows what your workspace can read and do.
A little curiosity goes a long way.Replace mk_your_token with the token you created. Keep it private.
claude mcp add --transport http mrkeyword \
https://app.mrkeyword.io/mcp \
--header "Authorization: Bearer mk_your_token"Ask in plain English. The tool names below show where each answer comes from.
Which of my pages is Google actually ranking for “emergency plumber near me”?
get_page_keywordsWhat is hurting this site today, and what should I do first?
get_daily_issuesHow has search performance moved since last month?
get_site_summaryWhich keywords dropped this week, and by how much?
get_rank_summary get_rankingsShow me the queries I am on page two for — the ones worth one afternoon.
get_search_queriesWhat did the last crawl find, grouped by how many pages it affects?
get_site_audit get_audit_issuesAre any of my programmatic templates thin or near-duplicate?
get_page_templatesHow many people search for “emergency plumber” in the UK each month? (uses one keyword lookup)
research_keywordSummarise last month for the client, with the sources.
get_site_summary get_reportExample questions, not recorded answers. Explore the tools in the developer reference.
Choose a built-in prompt when your client lists them. Each one gathers the tools it needs and writes up the result.

weekly_seo_reviewWeekly rank review for one site: what moved, what needs attention, and five actions for this week.
fix_my_top_issuesWalk the latest site crawl: what is broken, grouped by category, with concrete fix steps per issue.
find_keyword_opportunitiesTurn near-miss Search Console queries into a prioritised list, sized with live MrKeyword search volume when you agree to spend lookups.
client_reportWrite a client-ready SEO report for one site from rankings, search queries and the latest site audit.

Add the HTTP MCP server with the command above, then ask about your workspace in plain English.
View connection stepsOpen Customize → Connectors → Add custom connector, choose No sign in and add your token as a request header.
View connection stepsUse the HTTP MCP configuration in .cursor/mcp.json, with your workspace’s bearer token.
Other clients need HTTP MCP support and an authorization header. Check your client’s documentation. The same token also works with the REST API.
It works with any client that speaks the Model Context Protocol over HTTP. We test Claude Code, the Claude desktop app and Cursor, and the same URL and bearer token work from a script or plain curl. We are not going to list ChatGPT as supported, because what its clients support changes and we would rather you checked your own client than took our word for it.
No. You create a token in Settings → Connections, paste one line into your assistant, and ask questions in English. The developer reference exists for people who want to call the endpoint directly, not because you have to.
One workspace: its websites, Search Console performance, tracked keyword positions and history, the queries you appear for, crawl results and audit issues, saved reports, content briefs and your plan usage. 27 tools in total. It cannot read anything outside that workspace.
No. It cannot touch your website, your Google account or your billing under any setting. Within MrKeyword, a token is read-only unless you tick “Allow this token to make changes” when you create it, which unlocks five tools — tracking keywords, setting a target page, annotating, starting a crawl and running a saved report. Every one of those is written to the workspace audit log.
No, and it is worth being precise. There is no MrKeyword process that goes off and edits your site. What exists is a data source your assistant can query, plus tools that can queue work you asked for. The judgement and the publishing stay with you.
No. Connecting an assistant has no separate charge on any plan, including Free. Two tools use the workspace's allowances — tracking keywords and starting a crawl — exactly as they would in the app. Fair-use limits apply at 120 calls a minute per token.
The tools return real rows with an as_of date and a named source, and the server's own instructions tell the model the rules it has to repeat: positions are period averages and not live ranks, and search volume comes only from the two keyword tools, fetched live from Google Keyword Planner and paid for with lookup credits. A model can still phrase something loosely, which is why every answer can be traced back to the tool that produced it.
Your assistant can query the data you connect. You decide what it can change, and every answer still deserves your judgement.
Create a token, paste one line, and ask it anything. Free forever, no credit card.
