Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AccuRanker MCP Add 'emergency plumber denver' to acmeplumbing.com and tag it Denver services."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Yes, Claude, ChatGPT and other AI agents can work in your AccuRanker account. AccuRanker has its own ChatGPT app and documents a custom MCP connector for Claude. Cotlet.dev connects your own signed-in AccuRanker account to any AI agent, so you can ask in plain words and the AI adds keywords and lists your ranks for you.
Add these 20 keywords to my acmeplumbing.com domain and track them in Google US on desktop and mobile.
List all keywords for bluebottlebakery.com with their current rank and the change over the last 7 days.
Which of my keywords dropped more than 5 positions since Monday? Show the page that ranks for each.
Add "emergency plumber denver", "water heater repair denver" and "drain cleaning denver" and tag them "Denver services".
Show my 10 keywords with the highest search volume that rank between position 11 and 20.
Related MCP server: DinoRank MCP Proxy
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.
Copy .cursor/mcp.json from this repo into your project:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}This repo is a real MCP server. It speaks MCP over stdio, lists its AccuRanker tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.
{"mcpServers":{"accuranker":{"command":"uvx","args":["accuranker-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t accuranker-mcp .
docker run -i --rm -e COTLET_API_KEY accuranker-mcpTools: accuranker_guide, accuranker_status, accuranker_open, accuranker_read, accuranker_click, accuranker_type, accuranker_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
Python 3.10+, nothing else to install. From PyPI:
pip install accuranker-mcp # or run it once: uvx accuranker-mcp connect
accuranker-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 accuranker_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 accuranker_agent.py status # is AccuRanker ready in your Cotlet.dev account
python3 accuranker_agent.py guide # AccuRanker screens and sign-in link
python3 accuranker_agent.py read # open AccuRanker, read the page, close the browser
python3 accuranker_agent.py tools # list Cotlet.dev tools
python3 accuranker_agent.py serve # start the stdio MCP server (same as no argument)Does AccuRanker have an API?
AccuRanker has an official API and an official MCP server (checked 23 Oct 2026). The Read API and Write API (both v4) come with API access at no additional cost, but need a developer and an API token. Cotlet.dev works in your own signed-in AccuRanker account, so your AI agent can add keywords and check your rankings with no API key and no code.
How do I connect AccuRanker to ChatGPT?
Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to AccuRanker once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no AccuRanker API key.
Is there a way to use Claude with AccuRanker?
Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1 as a custom connector. Claude then works in your own AccuRanker account.
Is there an AccuRanker MCP server?
Yes, AccuRanker documents its own MCP connector for Claude. Cotlet.dev is also a hosted MCP server that works in your AccuRanker account for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.
What is AccuRanker Search Intelligence?
AccuRanker Search Intelligence is AccuRanker's official app in the ChatGPT Plugin directory. Cotlet.dev is another way in: one connector, https://cotlet.dev/mcp/v1, that works in your own AccuRanker account from ChatGPT, Claude and any other AI agent.
Start free: https://cotlet.dev/signup?app=accuranker&utm_source=github&utm_medium=readme&utm_campaign=accuranker
Click a numbered element on the current AccuRanker page.
Inputs: element (required).
Close the AccuRanker browser session when the work is done, so credits stop running.
Inputs: no named parameters.
How to work in AccuRanker (add keywords and check your rankings): its screens and the sign-in link. Call this first.
Inputs: task.
Open a AccuRanker page in your signed-in Cloud Browser (default https://app.accuranker.com) to work with add keywords and check your rankings.
Inputs: url.
Read the current AccuRanker page: its text and numbered buttons, links and fields.
Inputs: element.
Check that your Cotlet.dev account and AccuRanker are ready: account, credits and AccuRanker connection.
Inputs: no named parameters.
Type text into a numbered field on the current AccuRanker page.
Inputs: text (required), element (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool has a clearly distinct role in a browser automation workflow: guidance, status check, open, read, click, type, and close. There is no meaningful overlap between reading page state, clicking elements, and typing into fields.
All tools use the consistent accuranker_ prefix, and most names are concise action verbs. accuranker_guide and accuranker_status are noun-like exceptions, but they remain understandable and predictable.
Seven tools are well-scoped for a guided browser session in AccuRanker. Each tool supports a necessary step in the workflow without unnecessary surface area.
The set covers the essential browser-session lifecycle: guide, readiness check, open, inspect, interact, and close. Minor gaps such as explicit navigation, scrolling, or waiting controls exist but can usually be handled through links, clicks, and page reads.
Live SEO intelligence, rank tracking, site audits, and backlink analysis for AI agents.
Connect AI agents to your AI visibility and SEO data: competitors, citations, GSC, GA4, Bing.
An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.
Google rank checker MCP: live positions, ranked keywords, competitor domains and keyword gaps. Check a domain's live Google positions for up to 10 keywords per call, retrieve ranked keywords, find organic competitors and compare competitor keyword gaps. Results are snapshots, not built-in scheduled tracking or ranking history. Use to check current Google positions or research competitor keywords. This is a focused SEO Data subset. Use Search Console instead for your own connected site's historical performance; this connection does not schedule future checks. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Check my domain's live Google positions for these five keywords in the US after I approve the per-keyword API-credit spend. - Within my approved API-credit budget, show keywords the supplied domain currently ranks for. - Find competitor domains and keyword gaps for my domain after confirming the API-credit cost. Do not imply this sets up scheduled tracking. Docs: https://docs.crakseo.com/mcp-servers/rank-tracker
