---
title: "Minds MCP Server for ChatGPT, Claude, and Cursor | Minds"
canonical_url: "https://getminds.ai/mcp/overview"
last_updated: "2026-08-13T13:03:20.953Z"
meta:
  description: "Connect the Minds MCP server to compatible AI clients and agents for Minds, Groups, Panels, guided Studies, analytics, and export workflows."
  "og:description": "Connect the Minds MCP server to compatible AI clients and agents for Minds, Groups, Panels, guided Studies, analytics, and export workflows."
  "og:title": "Minds MCP Server for ChatGPT, Claude, and Cursor | Minds"
  "twitter:description": "Connect the Minds MCP server to compatible AI clients and agents for Minds, Groups, Panels, guided Studies, analytics, and export workflows."
  "twitter:title": "Minds MCP Server for ChatGPT, Claude, and Cursor | Minds"
---

Minds

Minds Team

# **Minds MCP Server for ChatGPT, Claude, and Cursor**

The Minds Model Context Protocol server connects compatible AI clients and agents to synthetic research workflows. It advertises a curated 18-tool surface for interactive assistants and registers 35 canonical tools across Minds, Groups, Panels, Studies, knowledge, chat, analytics, and exports.

Minds provides a Model Context Protocol (MCP) server that allows AI assistants to create synthetic research panels, run multi-perspective surveys, and interact with AI Minds directly. This enables seamless integration with tools like ChatGPT, Claude Desktop, Cursor, and other MCP-compatible clients.

## What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external tools and data sources. With our MCP integration, you can:

- Create and manage AI Minds (experts, personas, digital twins)
- Build research panels with groups of domain experts
- Run survey-style questions across multiple perspectives
- Get statistical analytics on panel responses
- Export branded PDF reports, markdown summaries, or raw data
- Organize Minds into reusable groups
- Create grounded audiences from briefs or respondent datasets
- Plan, explicitly confirm, run, and resume durable research Studies
- Manage knowledge, Formations, lifecycle actions, and stateful chats

## MCP Server URL

```
https://getminds.ai/mcp
```

For setup instructions by client, see the [Minds MCP setup guide](https://getminds.ai/mcp/setup). For all 35 canonical tools and the 18-tool advertised surface, see the [Minds MCP tools reference](https://getminds.ai/mcp/tools). Agent authors should also read the [MCP operating guide for agents](https://getminds.ai/mcp/agents).

## Authentication

The MCP server supports two authentication methods:

- **OAuth 2.1** (recommended) — Clients like ChatGPT and Claude Desktop handle this automatically. You'll be prompted to log in to your Minds account when connecting.
- **API Key** — For programmatic access, generate a key at Settings → API Keys (starts with `minds_`). Pass as `Authorization: Bearer minds_your_key`.

## Interactive Preview

The Response Widget renders panel results and chat conversations directly inside compatible MCP clients (ChatGPT, Claude Desktop, Cursor, VS Code). Click the tabs to see different question types, and click avatars to explore Mind details.

**Interactive demo **

### **Explore an MCP response **

Switch response formats, then select a Mind avatar to inspect the persona, sources, and reasoning behind the answer. ## Compatible Clients | Client | Tools | Widget | Auth | Setup |
| --- | :---: | :---: | :---: | --- | | **ChatGPT** | 15 advertised | Yes | OAuth | Settings → Connected Apps | | **Claude Desktop** | 15 advertised | Client-dependent | OAuth or API key | Customize → Connectors | | **Claude Code** | 15 advertised | No | API key | `claude mcp add --transport http` | | **Cursor** | 15 advertised | Client-dependent | OAuth | Settings → MCP | | **Langdock** | 15 advertised | No | OAuth | Integrations → Add MCP | | **VS Code (Copilot)** | 15 advertised | Client-dependent | OAuth | Settings → MCP Servers | | **Windsurf** | 15 advertised | No | API key | MCP settings |

All clients receive clickable links to open results in the Minds webapp, regardless of widget support.

## Advertised versus canonical tools

`tools/list` returns 18 curated tools designed for ordinary interactive research. The server also keeps 17 additional canonical lifecycle and compatibility tools registered, for 35 canonical tools in total. Explicit integrations can call those tools by canonical name when the client supports configured or direct tool calls. This split keeps the default model surface focused while preserving the full supported capability contract.

Tool aliases may remain callable for compatibility, but agents should always use canonical names from the [tools reference](https://getminds.ai/mcp/tools).