Integrate Searchable Data Directly to Claude Code and Cursor with MCP

The way we optimize websites is changing.

As AI-native search engines like ChatGPT, Claude, and Perplexity become the primary way users discover information, the "SEO workflow" is shifting from spreadsheets and dashboards into the very AI tools that are doing the searching.

Today, we're releasing the Searchable MCP Server, an integration that brings Searchable's AI visibility data and site audit engine directly into your AI workflow.

Your assistant can now see exactly how your brand is being cited across the AI landscape.

What's New: The Searchable MCP

The Model Context Protocol (MCP) is an open standard that enables AI models to safely access external data. By implementing this for Searchable, we've turned your AI assistant into a specialized AEO consultant.

With the Searchable MCP, you can now:

Query Visibility in Real-Time: Ask your AI assistant, "How often is my brand mentioned in Claude compared to ChatGPT?" and get instant, data-backed answers.
Audit While You Build: If you're a developer using Cursor, you can ask, "What are the critical technical issues on this page?" and get a list of fixes while you have the code open.
Analyze Citations: Understand which pages are driving your AI visibility and which ones need more AEO (AI Engine Optimization) work.
Get Actionable Fixes: Beyond just finding issues, the MCP server provides specific recommendations like exact meta-tag improvements or content adjustments, tailored to AI readability.
Work Through Opportunities and Tasks: Chat with your Cursor or Claude Code agent about your existing Opportunities and Tasks to directly resolve outstanding work without leaving your IDE.

Available Tools

The Searchable MCP exposes seven tools that your AI assistant can use:

Tool	What It Does
`list_projects`	Lists all your Searchable projects with names, domains, and IDs
`get_visibility_summary`	Overall AI visibility score, mention rate, and score changes over time
`get_visibility_details`	Platform-by-platform breakdown (ChatGPT, Claude, Perplexity, Gemini)
`get_website_issues`	Current issues grouped by severity (critical, high, medium, low)
`get_page_audits`	Technical, content, and AEO scores for each monitored page
`get_monitored_pages`	All tracked pages with issue counts
`get_issue_details`	Deep dive into specific issue types with fix recommendations

Why It Matters: Closing the Optimization Loop

For years, SEO has been a game of "guess and check." In the new era of AI Search, the feedback loop needs to be faster.

By integrating Searchable directly into tools like Cursor, Claude Code, and Cline, we're removing the friction between insight and action.

You no longer have to export a PDF, read it, and then go back to your code. You simply ask your AI agent to audit the site, and then tell it to fix the issues it finds.

This is the first step in our mission to make AI visibility as transparent and actionable as traditional search rankings.

Get Started

The Searchable MCP is available today. You can connect it to your workflow in less than two minutes.

1. Generate an API Key

Log in to Searchable, go to Settings → Integrations → Cursor MCP, and create a new API key. It will start with sea_.

2. Configure Cursor

Add the following to your .cursor/mcp.json file:

{
"mcpServers": {
  "searchable": {
    "url": "https://searchable-mcp-production.searchable.workers.dev/sse",
    "headers": {
      "Authorization": "Bearer YOUR_API_KEY"
    }
  }
}
}

Replace YOUR_API_KEY with the key from Integrations.

3. Configure Claude Code

For Claude Code, run this command in your terminal:

claude mcp add searchable --transport http https://searchable-mcp-production.searchable.workers.dev/sse --header "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with the key from Integrations.

4. Start Querying

Restart Cursor or Claude Code, then try asking:

"What is my AI visibility score for my main project?"
"Show me the page audit scores for my blog."
"What are the critical issues on my site and how do I fix them?"

Explore with AI

In Cursor: Use get_website_issues to pull your site issues, then ask Cursor to fix them directly in your codebase. This is the best use case we've seen so far.

In Claude Code: Use get_visibility_details to see a platform-by-platform breakdown of your brand's performance. Ask follow-up questions like "Why is my Perplexity score lower than ChatGPT?"

The MCP pulls live Searchable data into your AI workflow including visibility scores, site audits, and page scores.

What's Next

This is the foundation for deeper AI-native workflows. Coming soon:

Auto-resolution tracking: See when issues you've fixed are detected as resolved
Competitive visibility queries: Ask how you compare to competitors in AI responses
Direct remediation: Let your AI assistant propose and apply fixes based on audit findings

The Searchable MCP is live now.

We can't wait to see how you use these tools to build a more visible web.

Integrate Searchable Data Directly to Claude Code and Cursor with MCP