# Built for Cursor: run synthetic market research through a remote MCP server

**URL:** <https://forum.cursor.com/t/built-for-cursor-run-synthetic-market-research-through-a-remote-mcp-server/167229>\
**Category:** Built for Cursor\
**Tags:** mcp\
**Created:** [August 1, 2026, 7:53pm UTC](https://forum.cursor.com/t/built-for-cursor-run-synthetic-market-research-through-a-remote-mcp-server/167229 "2026-08-01T19:53:59Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![getminds](https://avatars.discourse-cdn.com/v4/letter/g/76d3ee/32.png) [@getminds](https://forum.cursor.com/u/getminds)\
**Post date:** [August 1, 2026, 7:53pm UTC](https://forum.cursor.com/t/built-for-cursor-run-synthetic-market-research-through-a-remote-mcp-server/167229/1 "2026-08-01T19:53:59Z")

</div>

We built a Cursor integration for running an evidence-grounded first research pass without leaving the editor.

Typical workflow:

1. Define a target audience from a plain-language brief.
2. Create a panel around a concrete product or marketing decision.
3. Ask a focused question or plan a multi-question study.
4. Inspect segment disagreement and minority views.
5. Export the result as PDF, CSV, XLSX, JSON, or Markdown.

Add the remote server in Cursor Settings → MCP:

```json
{
  "mcpServers": {
    "minds": {
      "type": "http",
      "url": "https://getminds.ai/mcp"
    }
  }
}

```

OAuth is preferred; scoped Minds API keys also work where secure custom headers are supported. The public repository contains the Cursor plugin manifest and the shared documentation source:

> **[GitHub - minds-ai-co/minds-mcp: Docs for the Minds MCP server: run AI market...](https://github.com/minds-ai-co/minds-mcp)**
>
> Docs for the Minds MCP server: run AI market research with synthetic customer panels from ChatGPT, Claude, and Cursor.

Setup and research-scope notes:

> **[Minds MCP Setup for ChatGPT, Claude, Cursor, and… | Minds](https://getminds.ai/mcp/setup?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=cursor-built-for-cursor)**
>
> Set up the Minds MCP server with ChatGPT, Claude Desktop, Cursor, VS Code, OpenRouter, Open WebUI, and API key authentication.

This is decision support, not a substitute for representative human fieldwork. I would welcome feedback on the tool boundaries and which research workflow is most useful inside Cursor.