Run AI market research: synthetic customer panels for concept testing, message testing, segments.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Minds: Synthetic Market Research Panels.
list_groupsList your saved Audiences, segments, and persona collections.
create_group_from_briefBuild a grounded synthetic Audience from a population brief via deep web research.
ask_groupAsk, survey, or poll a single Audience and get per-respondent answers.
list_panelsList your panels, studies, surveys, and focus groups.
create_panelCreate a panel or study from a research goal.
ask_panelAsk one straightforward question across a whole panel.
Run AI market research from your assistant: synthetic customer panels for concept testing, message testing, and segment comparison.
Endpoint: https://getminds.ai/mcp (streamable HTTP)
Docs: https://getminds.ai/mcp/setup
Quick-start guide: https://minds-ai-co.github.io/minds-mcp/
Technical reference: https://minds-mcp.readthedocs.io/en/latest/
GitBook: https://minds-1.gitbook.io/minds-mcp/
Client compatibility: https://minds-mcp-compatibility.pages.dev/
Setup generator: https://minds-mcp-setup-generator.netlify.app/
Public API explorer: https://minds-api-explorer.vercel.app/?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=mcp-repository-api-explorer
API + MCP integration lab: https://minds-api-mcp-integration-lab-bba685.gitlab.io/?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=mcp-repository-integration-lab
Archived release: https://doi.org/10.5281/zenodo.21711429
Auth: OAuth 2.1 with PKCE, or a Minds API key
This repository is documentation for a hosted MCP server. There is no code to install or run. The server is operated by Minds and the implementation lives in our application, not here.
reference/ is the single source for maintained integration content. Read the
Docs and GitBook publish the same Markdown through repository sync. GitHub Pages,
Cloudflare Pages, and the Netlify setup generator are intentionally thin,
platform-specific surfaces; Zenodo preserves versioned release snapshots. See
DOCUMENTATION.md for the publishing contract.
Minds is a synthetic market research platform. This MCP server lets ChatGPT, Claude, Cursor, and any other MCP client run customer research end to end without leaving the assistant.
Describe an audience in a brief ("German Gen Z grocery shoppers", "enterprise IT buyers in fintech") and the server runs deep web research to ground that audience in government statistics, peer-reviewed studies, and industry reports rather than in generic model priors. Then ask the panel a question, run a structured study, and export the results.
Typical jobs:
Studies run durably server side, so a long study survives the chat session that started it. Results export to PDF, CSV, XLSX, JSON, and Markdown.
Scope. Minds does not replace representative human fieldwork. It replaces the slow first pass: sharpening the question, surfacing objections, and deciding which assumptions deserve real-respondent validation.
Settings, then Connected Apps, then add https://getminds.ai/mcp and authorize via
OAuth. Panel results render as interactive widgets inline.
Customize, then Connectors, then add https://getminds.ai/mcp as a remote
connector and authorize via OAuth.
Settings, then MCP, then add https://getminds.ai/mcp and authorize via OAuth.
The repository also contains a Marketplace-ready Cursor plugin manifest at
.cursor-plugin/plugin.json; its MCP configuration is intentionally kept in
cursor.mcp.json so the shared Agent Plugins configuration can retain the
portable streamable-http transport name.
The root plugin.json and mcp_config.json make this repository an Antigravity
plugin. Antigravity discovers OAuth from the hosted endpoint and prompts you to
authenticate. You can also add Minds directly in the Antigravity MCP manager
with the server URL https://getminds.ai/mcp.
Gemini CLI remains supported for Google Cloud enterprise and API-key users. Its
legacy extension manifest stays available as gemini-extension.json.
The repository includes the shared plugin package at
.codex-plugin/plugin.json and its remote server configuration in .mcp.json.
The public directory listing uses the same hosted endpoint and maintained
reference content.
Add https://getminds.ai/mcp as a remote MCP server. Full per-client instructions,
including API key setup, are at https://getminds.ai/mcp/setup.
Generate one in the Minds app under Settings, then API Keys. Keys start with
minds_ and are passed as Authorization: Bearer minds_....
| Tool | What it does |
|---|---|
list_groups | List your saved Audiences, segments, and persona collections. |
create_group_from_brief | Build a grounded synthetic Audience from a population brief via deep web research. |
ask_group | Ask, survey, or poll a single Audience and get per-respondent answers. |
list_panels | List your panels, studies, surveys, and focus groups. |
create_panel | Create a panel or study from a research goal. |
ask_panel | Ask one straightforward question across a whole panel. |
get_panel_status | Check panel composition and live progress on in-flight questions. |
export_panel | Export panel results as PDF, CSV, XLSX, or JSON. |
plan_panel_study | Draft a structured research plan for multi-question studies, asset audits, and MaxDiff. |
run_panel_study | Execute a confirmed study plan as a durable server-side run. |
get_panel_study | Check durable progress, artifacts, and method calculations for a running study. |
list_research_methods | List supported research methods and which of them can actually execute. |
get_panel_summary | Return a whole-study summary with semantic blocks and heatmaps. |
list_study_drafts | List reusable study-plan drafts in the connected workspace. |
save_study_draft | Save a study plan as a reusable draft before execution. |
Research methods: MaxDiff runs through a deterministic adapter. Conjoint is
planned and cannot execute yet. Call list_research_methods for the current
state rather than assuming.
https://getminds.ai/.well-known/mcp/server-card.jsonhttps://getminds.ai/.well-known/oauth-protected-resourceai.getminds/mindsShowcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/minds-synthetic-market-research-panels-3)<a href="https://allmcps.com/mcp/minds-synthetic-market-research-panels-3"><img src="https://allmcps.com/api/badge/minds-synthetic-market-research-panels-3?style=directory" alt="Minds: Synthetic Market Research Panels on AllMCPs" /></a>