VS Code setup guideData AI Search × VS Code

Use Data AI Search in VS Code

VS Code runs MCP servers for GitHub Copilot Chat in agent mode. Add Data AI Search as an HTTP server and Copilot can read your brand's Insights and audits, and work through the Website Audit's fixes in your workspace.

Setup01

Connect VS Code 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 the server

    Run MCP: Add Server from the Command Palette, pick HTTP, paste the URL and name it intura. Choose Global to keep it in your user profile, or Workspace to write .vscode/mcp.json. You can also add the entry below to mcp.json by hand. VS Code uses "servers", not "mcpServers".

    .vscode/mcp.json
    {
      "servers": {
        "intura": {
          "type": "http",
          "url": "https://api.dataaisearch.com/mcp?api_key=YOUR_API_KEY"
        }
      }
    }
  3. 3

    Start it and pick the tools

    Run MCP: List Servers, select intura and start it; VS Code asks you to trust it the first time. In the Chat view, switch to Agent and open the tools picker to see its three tools.

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 VS Code 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, which pages on [brand]'s site have the most Website Audit problems?”
  • “What are [brand]'s buyers asking AI about pricing? Draft answers for our FAQ page.”
  • “List the open Website Audit actions for [brand], highest priority first.”
  • “What's [brand]'s Visibility Score, and which cluster is weakest?”
Good to know03

Before you rely on it

  • Prefer Global for this server: .vscode/mcp.json is usually committed, and the URL contains your key.
  • The top-level key in VS Code's mcp.json is "servers". A config copied from Cursor or Claude uses "mcpServers" and won't load.
  • Copilot asks before each tool call. You can allow a tool for the session; keep approving the audit tools one call at a time.
  • Untick ai_visibility_audit and website_audit in the tools picker for a read-only setup.
If it doesn't connect
intura isn't in the tools picker
Check that the chat is in Agent mode and the server is running (MCP: List Servers → intura → Start).
The server fails to start
Open MCP: List Servers → intura → Show Output. Check that type is "http" and the URL still has its api_key.
"MCP integrations aren't available on your plan"
The workspace is on the Free plan. Upgrade to Starter or higher.
FAQ04

VS Code and Data AI Search: questions

Do I need GitHub Copilot?

Yes. In VS Code, MCP tools are used by Copilot Chat in agent mode.

Which transport should I pick?

HTTP. Set "type": "http"; the server speaks Streamable HTTP, so there's nothing to run locally.

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