Give your AI agent your AEO data

Connect Claude Code, Cursor, or any MCP client over OAuth. Your agent reads your visibility reports and citations across ChatGPT, Perplexity, Google AI Mode, Claude, Gemini, and Grok, runs new reports, and ships the fixes, all from your answer engine optimization (AEO) data, without leaving the tools you already work in.

Connect now Read the docs

OAuth 2.1
No key to paste
Works with any MCP client

Connect Rank Prompt

claude mcp add --transport http --scope user rankprompt https://mcp.rankprompt.com/mcp

How it works

Nothing to install, nothing to paste

We run the server for you. Add one line to your AI tool, sign in with your Rank Prompt account, and your agent works from your AI visibility data a minute later.

In Claude Code you run /mcp and sign in through the browser: no API key to copy, paste, or rotate. Tools without a browser sign in can use a key from the Developers page.

setup One command or one config line
sign in Your Rank Prompt login
works in and any MCP client
answers from

Connect

Connect in 30 seconds

Pick your client, copy the snippet, then approve access in the browser.

Terminal

claude mcp add --transport http --scope user rankprompt https://mcp.rankprompt.com/mcp

Run the command, then /mcp to sign in over OAuth. No key to paste.

~/.cursor/mcp.json

{
  "mcpServers": {
    "rankprompt": {
      "url": "https://mcp.rankprompt.com/mcp"
    }
  }
}

Add to your Cursor MCP config, then approve the OAuth prompt in the browser.

claude_desktop_config.json

{
  "mcpServers": {
    "rankprompt": {
      "url": "https://mcp.rankprompt.com/mcp"
    }
  }
}

Settings, Developer, Edit Config. Paste, restart Claude Desktop, then approve access.

mcp.json

{
  "mcpServers": {
    "rankprompt": {
      "url": "https://mcp.rankprompt.com/mcp"
    }
  }
}

Any MCP client with remote Streamable HTTP support. Point it at the URL and authenticate over OAuth, or paste a pass-through API key.

What your agent can do

Ask in plain words, get the work done

Your agent reads your reports, citations, and audits, then acts on them inside the tools you already use. A few of the things teams ask for on day one.

Pull my latest visibility report and fix the top three issues on the site.

The pages that lose answers, found and edited in your repo, ready for review.
Which sites cite our competitors but not us? Draft outreach for the best five.

A shortlist of sources you can actually reach, with a pitch written for each.
Run a new report and tell me what changed since last week.

Fresh answers from every engine and a plain summary of where you gained and lost.
Set up our new client and measure them every Monday.

The brand researched, prompts in place, and a weekly report running on its own.
Audit our pricing page for AI search and open a PR with the fixes.

An SEO and AEO score for the page and a pull request with the changes.

Trust

Built to connect safely

You decide what the agent can see and change, and you can cut it off at any time.

Sign in, never paste

You connect with your Rank Prompt login in the browser. No key lands in a config file or your shell history.

You approve each app

Every AI tool asks for access on a consent screen before it sees any of your data.

Only the brands you choose

Access follows your permissions and brand limits, so an agent working for one client never sees another.

Revoke anytime

Credentials are encrypted at rest, and you can shut off a connection whenever you want.

Plan

MCP access is included on every plan, free included. Your plan sets the monthly request allowance, and work that costs us money costs credits.

See plans

No OAuth flow in your client? Mint a pass-through key on the Developers page.

FAQ

MCP questions

Everything teams ask before they connect an agent. Email us if your question isn't covered.

Still have questions? Contact our team

What is the Model Context Protocol (MCP)?

MCP is an open standard for connecting AI assistants to external tools and data. The Rank Prompt MCP server puts your AI visibility data, your brands, reports, and citations, within reach of any AI agent that speaks MCP.

Which clients can connect?

Any MCP client that supports remote Streamable HTTP servers, including Claude Code, Cursor, and Claude Desktop. Point the client at https://mcp.rankprompt.com/mcp and authenticate over OAuth.

Do I have to paste an API key?

In Claude Code, no. Run /mcp and sign in through your browser over OAuth. Clients without a built-in OAuth flow can use a pass-through API key minted on the Developers page in your workspace.

What can the agent actually do?

Read your visibility across ChatGPT, Perplexity, Google AI Mode, Claude, Gemini, and Grok, compare you with competitors, find the sources worth pitching, run new reports, audit pages, set up brands and schedules, and turn what it finds into changes in the tools you already use.

Is the MCP server secure?

Yes. You sign in with OAuth 2.1 in the browser and approve each app on a consent screen. Access follows your permissions and brand limits, credentials are encrypted, and you can revoke a connection at any time.

What plan do I need?

Any plan, including free. What your plan changes is the monthly request allowance and which features are unlocked: automated brand research, audits, content briefs, CMS publishing, webhooks and the premium engines need Starter or above. Running work costs credits, which you can top up from the agent itself.

How is the MCP server different from the public API?

Same data, different entrypoint. The /v1 REST API is for your backend to pull data; the MCP server lets your AI agent read and act on that data conversationally, inside the tools you already work in.

Is the MCP server live?

Yes. It runs as a hosted remote server at mcp.rankprompt.com/mcp, alongside the public /v1 API and outbound webhooks.

Free AI visibility report first · 7-day trial on any plan

Bring Rank Prompt into your agent

Start a free trial, connect over OAuth, and let your AI agent work from your real AI visibility data.

Start free trial Connect now