Skip to content
MCP server

Sunzu

MCP server running synthetic-human user research tests from Claude, ChatGPT, Cursor and VS

Answers · sign-in required (OAuth)

The server answered yesterday with a sign-in request for OAuth (HTTP 401), so we could not list its tools.

Install

Sunzu is an MCP server for product data. It runs as a hosted remote server, so there is nothing to install locally.

Pricing
Free trial
Platforms
Web, CLI, API
Runs
Remotely
Access
Needs sign-in (OAuth)
Version
1.0.0
Listing updated

Similar MCP servers

Install

Run in a terminal

claude mcp add --transport http sunzu https://app.sunzu.com/mcp

Add to Settings → Connectors → Add custom connector

https://app.sunzu.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "sunzu": {
      "url": "https://app.sunzu.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "sunzu": {
      "type": "http",
      "url": "https://app.sunzu.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sunzu": {
      "serverUrl": "https://app.sunzu.com/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://app.sunzu.com/mcp

Enter a Name (for example "Sunzu"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for OAuth sign-in. If its docs give you an OAuth client ID and secret, enter them in the form's OAuth Client ID and Client Secret fields.

Full Grok Bot setup guide

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "sunzu": {
      "type": "http",
      "url": "https://app.sunzu.com/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

About Sunzu

Sunzu connects your AI assistant to a user research service built on synthetic participants. Instead of scheduling calls, you describe a concept, ad, prototype or website to your assistant, and it launches depth interviews, concept tests, usability tests or content tests against audiences you already have in your workspace.

The connector signs in through OAuth in the browser, then lets the assistant list audiences, quote a study in credits before it starts, launch it and read the finished report back in the chat. Usability tests can also run against an app on your own machine through the companion command-line tool.

It suits product managers, founders and agencies who want quick directional signals before committing to research with real people. Findings are simulated, so they are best used alongside, not in place of, conversations with actual customers.

Tools this server provides (20)

Taken from the project documentation; the running server may differ.

get_workspace
The workspace this connection uses.
get_credit
Credits left on the plan.
list_audiences
Audiences available to study.
add_library_audience
Adds free library audiences.
quote_study
Price of a study in credits before it starts.
prepare_upload_page
Prepares an upload page for concepts, ads or prototypes.
prepare_stimulus_upload
Uploads stimulus material for a study.
get_uploaded_files
Lists uploaded study files.
start_depth_interview
Starts a depth interview study.
plan_depth_interview
Creates a depth interview plan for review.
update_study_plan
Updates a study plan.
start_concept_test
Starts a concept test with 1 to 3 concepts.
start_ad_test
Starts an ad or content test with 1 to 5 versions.
start_usability_test
Starts a usability test on a website, prototype, Figma flow or local app.
launch_study
Launches a study created for review.
resume_study
Resumes a study.
wait_for_study
Waits for a study to finish.
get_study_status
Reports the status of a study.
list_studies
Lists studies in the workspace.
get_report
Retrieves a study report.

What it does

Four research methods
Runs depth interviews, concept tests, usability tests and content or ad tests from within an AI chat.
Credit quoting before launch
Shows the cost of a study in credits so you can decide before anything is run.
Reports read back in chat
Lets the assistant retrieve study status and summarise the resulting report for you.
Audience library access
Lists the audiences in your workspace and can add free library audiences to a study.
Command-line companion
Offers a CLI for logging in and running usability tests on a locally hosted app.
Connected-tool management
Lets you view and disconnect AI tools linked to your account at any time.

Good for

  • Test reactions to a product concept before building it
  • Compare several versions of an ad or piece of content
  • Run a usability check on a website or Figma prototype
  • Gather simulated interview feedback on a product idea
  • Review a study plan before launching it from your AI assistant

Pricing

Free trial, from $30 a month

Solo $30/mo with first month free; Team $100/mo; Enterprise from $2,000/mo

Prices change. Check sunzu.com before you buy.

Sunzu FAQ

Which AI clients can connect to Sunzu?

Claude (web, Desktop and Claude Code), ChatGPT, Cursor and VS Code with GitHub Copilot are all covered by the setup guide, and other MCP clients can connect by URL.

Can the connector buy plans or credits?

No. It can quote and launch studies that spend credits, but plans, credits and discount codes stay in the Sunzu app.

Is there a free option?

The Solo plan's first month is free, after which it costs $30 a month.

Where is data hosted?

Data is hosted in the EU or the US, depending on the plan's setup.

How do I add Sunzu to Claude Code?

Run this command in your terminal: claude mcp add --transport http sunzu https://app.sunzu.com/mcp

What are the best alternatives to Sunzu?

The closest alternatives to Sunzu are SOQVER business facts (SO4AG), AgentAPIHub — Walmart, Shopee, TikTok Shop, Shopify & WooCommerce Catalog MCP, AgentAPIHub — Walmart, Shopee, TikTok Shop, Shopify & WooCommerce Catalog MCP, SpecSource and HenryCrawl E-commerce MCP.

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Status: checked automatically by AIPoweredBot on 21 November 2026.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers