---
title: "MCP Tools Reference | Minds"
canonical_url: "https://getminds.ai/mcp/tools"
last_updated: "2026-05-19T11:20:03.342Z"
meta:
  description: "All 12 MCP tools for creating Minds, running panel research, and analyzing results."
  "og:description": "All 12 MCP tools for creating Minds, running panel research, and analyzing results."
  "og:title": "MCP Tools Reference | Minds"
  "twitter:description": "All 12 MCP tools for creating Minds, running panel research, and analyzing results."
  "twitter:title": "MCP Tools Reference | Minds"
---

Minds Team

# **MCP Tools Reference**

All 12 MCP tools for creating Minds, running panel research, and analyzing results.

# MCP Tools Reference

The MCP server exposes 12 tools organized into two categories.

## Minds & Groups

### list_minds

List all Minds owned by the authenticated user with optional search.

**Parameters:**

- `searchQuery` (optional): Filter by name using fuzzy search

**Example:**

```
"List my AI minds about marketing"
```

### create_mind

Create a new Mind — a synthetic expert, consumer persona, or digital twin.

**Parameters:**

- `name` (required): Name of the Mind
- `mode` (required): Training mode — `keywords`, `clone`, `link`, or `manual`
- `type` (optional): Type — `creative`, `expert`, or `user` (default: `expert`)
- `discipline` (optional): Area of expertise
- `keywords` (optional): Topics for training (required for `keywords` mode)
- `personaContext` (optional): Person to model (required for `clone` mode)
- `contextLink` (optional): URL to train from (required for `link` mode)
- `description` (optional): What this Mind specializes in

| Mode | Description | Required Fields |
| --- | --- | --- |
| `keywords` | Train from topic keywords | `keywords` |
| `clone` | Create a digital twin of a person | `personaContext` |
| `link` | Train from website content | `contextLink` |
| `manual` | Manual configuration | None |

### chat_with_mind

Send a message to a Mind and get a response. Supports multi-turn conversations and fuzzy name matching.

**Parameters:**

- `sparkId` (optional): Mind UUID (use this OR `sparkName`)
- `sparkName` (optional): Name with fuzzy matching (e.g., "my marketing expert")
- `message` (required): Message to send
- `conversationHistory` (optional): Previous messages for multi-turn context

### get_mind_status

Check training progress after creating a Mind.

**Parameters:**

- `sparkId` (required): Mind UUID

### list_groups

List all Mind groups visible to the user.

**Parameters:**

- `searchQuery` (optional): Filter by name using fuzzy search

### create_group

Create a named group of Minds for panel research.

**Parameters:**

- `name` (required): Group name (e.g., "Marketing Experts")
- `sparkIds` (required): Mind IDs to add — use `list_minds` to find IDs

## Panels (Multi-Mind Research)

### create_panel

Create a research panel that groups multiple Minds for comparative analysis.

**Parameters:**

- `name` (required): Name for the panel
- `groupConfigs` (optional): New groups to create inline — each with `name` and `sparkIds`
- `groupIds` (optional): Existing group IDs to attach

**Example:**

```
"Create a panel called 'Brand Perception Study' with two groups:
 - 'Marketing Experts' containing my SEO and Content Marketing minds
 - 'Consumer Insights' containing my Gen Z and Millennial minds"
```

### ask_panel

Submit a research question to all groups in a panel. Questions are automatically classified as scale, categorical, or qualitative.

**Parameters:**

- `panelId` (optional): Panel UUID
- `panelName` (optional): Panel name (fuzzy matched)
- `question` (required): Research question
- `groupIds` (optional): Only query specific groups

### list_panels

List all research panels with group composition and question counts.

**Parameters:**

- `searchQuery` (optional): Filter by name using fuzzy search

### get_panel_status

Get detailed panel information including in-progress questions, completed results, and export status.

**Parameters:**

- `panelId` (optional): Panel UUID
- `panelName` (optional): Panel name (fuzzy matched)

### get_panel_analytics

Compute statistical analytics across a panel's question history.

**Returns:**

- **Scale questions**: Mean, median, standard deviation, consensus, group rankings
- **Categorical questions**: Distribution, dominant category, cross-group divergence
- **Qualitative questions**: Theme clustering, shared themes, diversity index

**Parameters:**

- `panelId` (optional): Panel UUID
- `panelName` (optional): Panel name (fuzzy matched)

### export_panel

Export panel results as a report.

**Parameters:**

- `panelId` (optional): Panel UUID
- `panelName` (optional): Panel name (fuzzy matched)
- `format` (optional): `md` (default), `pdf`, or `json`

| Format | Description |
| --- | --- |
| `md` | Markdown report returned inline |
| `pdf` | Branded PDF with executive summary and recommendations. Async — use `get_panel_status` to check. |
| `json` | Raw structured data for downstream analysis |