> For the complete documentation index, see [llms.txt](https://minds-1.gitbook.io/minds-mcp/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://minds-1.gitbook.io/minds-mcp/index.md).

# Overview

Minds is a remote Model Context Protocol server for evidence-grounded synthetic market research. It lets an MCP-compatible assistant create Audiences, run Studies, inspect disagreement, and export structured results without leaving the assistant.

| Protocol detail | Value                                                                      |
| --------------- | -------------------------------------------------------------------------- |
| Remote endpoint | `https://getminds.ai/mcp`                                                  |
| Registry name   | `ai.getminds/minds`                                                        |
| Transport       | Streamable HTTP                                                            |
| Authentication  | OAuth 2.1 with PKCE (DCR or Client ID Metadata Documents) or Minds API key |
| Study execution | Durable, server-side runs                                                  |
| Exports         | PDF, DOCX, PPTX, Markdown, CSV, XLS, and SPSS SAV                          |

[Connect Minds to an MCP client](https://getminds.ai/mcp/setup?utm_source=content\&utm_medium=content\&utm_campaign=content-seo-mcp-reference\&utm_content=mcp-docs-overview)

## What it is for

Use Minds to:

* test concepts, messages, positioning, packaging, or campaign ideas;
* build an audience from a plain-language population brief;
* compare reactions between segments;
* surface objections and disagreement before committing budget;
* screen research hypotheses before representative fieldwork;
* export findings into a research or decision workflow.

Minds grounds a population in external evidence before generating synthetic respondents. Studies remain available server-side, so a long-running study can continue after the chat session that started it.

## The operating sequence

1. **Define the audience.** Describe the market, buyer group, or stakeholder set.
2. **Ground the population.** Minds researches statistics and relevant evidence.
3. **Create the Study.** Turn the decision or research goal into a Study.
4. **Run the questions.** Ask one question or execute a structured Study plan.
5. **Inspect and export.** Compare segments, inspect disagreement, and download results.

## Start here

* [Connect a client](/minds-mcp/connect.md) for ChatGPT, Claude, Cursor, VS Code, and other clients.
* [Use the practical cookbook](/minds-mcp/cookbook.md) for complete positioning, concept, and message-study recipes.
* [Browse this maintained reference on GitBook](https://minds-1.gitbook.io/minds-mcp/).
* [Check client compatibility](https://minds-mcp-compatibility.pages.dev/) for a compact transport and authentication matrix.
* [Generate a client configuration](https://minds-mcp-setup-generator.netlify.app/) for Claude Code, Cursor, VS Code, or a generic MCP client.
* [Explore the live public API contract](https://minds-api-explorer.vercel.app/?utm_source=content\&utm_medium=content\&utm_campaign=content-seo-mcp-reference\&utm_content=mcp-docs-api-explorer) across Studies, Audiences, Minds, research, and durable runs.
* [Choose an API or MCP integration path](https://minds-api-mcp-integration-lab-bba685.gitlab.io/?utm_source=content\&utm_medium=content\&utm_campaign=content-seo-mcp-reference\&utm_content=mcp-docs-integration-lab) with the live route recommender and production OpenAPI index.
* [Run a study](/minds-mcp/workflow.md) for a durable end-to-end workflow.
* [Browse the tools](/minds-mcp/tools.md) exposed by the remote server.
* [Understand the scope](/minds-mcp/scope.md) before using results in a decision.

The maintained product documentation is available at [getminds.ai/mcp/setup](https://getminds.ai/mcp/setup?utm_source=content\&utm_medium=content\&utm_campaign=content-seo-mcp-reference\&utm_content=mcp-docs-overview-guide).

## Citation and archived release

The versioned integration reference is preserved as an open software record:

Minds Developer Team (2026). *Minds MCP Integration Reference* (Version 2.0.0). <https://doi.org/10.5281/zenodo.21711429>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://minds-1.gitbook.io/minds-mcp/index.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.