Cursor setup guideData AI Search × Cursor

Add Data AI Search to Cursor

Cursor reads remote MCP servers from mcp.json. Add Data AI Search there and Cursor's agent can look up what AI search says about your brand and what the Website Audit found, then make the fixes in your code.

Setup01

Connect Cursor to Data AI Search

  1. 1

    Copy your server URL

    Sign in to the Data AI Search dashboard, open Integrations → MCP and copy the server URL. Your API key is already in it.

  2. 2

    Add it to mcp.json

    Open Cursor Settings → MCP (Tools & MCP in newer versions) and add a new MCP server, which opens ~/.cursor/mcp.json. Add the intura entry below and save. For one project only, put the same entry in .cursor/mcp.json in that project.

    ~/.cursor/mcp.json
    {
      "mcpServers": {
        "intura": {
          "url": "https://api.dataaisearch.com/mcp?api_key=YOUR_API_KEY"
        }
      }
    }
  3. 3

    Check that it's on

    Back in the MCP settings, intura should show a green dot and its three tools. Switch individual tools off there if you want the agent to only read.

Replace YOUR_API_KEY with your own key, or copy the full URL from Integrations → MCP in the Data AI Search dashboard, where it is already filled in. The URL is the key: anyone who has it can read your workspace and spend its credits.

What it can reach02

What Cursor can do with your data

The server has three tools, one per pillar. Each takes a brand name; ask about a brand the workspace doesn't have and the tool replies with the names it does have.

  • brand_insights

    Read-only. The real questions your brand's buyers ask AI, how AI answers them, who it names instead of you, keywords and segments.

    Tool reference
  • ai_visibility_audit

    Read the Visibility Score, prompts, clusters and next actions, or set the audit up, add questions and run them.

    Tool reference
  • website_audit

    Read the site audit, root causes, weakest pages and action list, or start, refresh, re-run and re-check a page.

    Tool reference
Try these first
  • “Using Data AI Search, list the Website Audit problems for [brand] and fix the ones in this codebase.”
  • “What do [brand]'s buyers ask AI that our docs don't answer? Suggest pages to add.”
  • “Read the AI Visibility next actions for [brand] and turn the top three into tasks for this repo.”
  • “I fixed /pricing. Ask the Website Audit to re-check that page.”
Good to know03

Before you rely on it

  • The global file (~/.cursor/mcp.json) keeps the key out of your repositories. If you use the project file, add .cursor/mcp.json to .gitignore.
  • Cursor asks before it runs a tool unless you've turned on auto-run. Keep auto-run off for the audit tools, which can spend credits.
  • Leave only brand_insights switched on for a read-only view of your data.
  • After editing mcp.json by hand, reload the window (Command Palette → Reload Window) if intura doesn't show up.
If it doesn't connect
intura shows a red dot
Open the server's log from the MCP settings. Usually the URL was pasted without its api_key, or the JSON has a trailing comma.
The agent doesn't call the tools
Use Agent mode, and name Data AI Search or the brand in your request.
"MCP integrations aren't available on your plan"
The workspace is on the Free plan. Upgrade to Starter or higher.
FAQ04

Cursor and Data AI Search: questions

Global or project mcp.json?

Global (~/.cursor/mcp.json) if you want Data AI Search in every project and your key out of git. Project (.cursor/mcp.json) if only one repository needs it.

Can Cursor change my audits?

Only through ai_visibility_audit and website_audit, and only when the agent calls an action such as run_prompts or rerun. Switch those two tools off in the MCP settings for a read-only setup.

What does it cost?

1 credit per call from your Data AI Search workspace. Setting up or running AI Visibility prompts and starting a Website Audit cost what they cost in the dashboard.

Setup guides for other assistants