For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
  • Workflows
    • Overview
  • Get Started
    • MCP Quick Start
    • API Quick Start
  • MCP Server
    • Overview
    • Installation
      • Overview
      • get_all_minds
      • search_minds
      • create_mind
      • get_signed_upload_url
      • upload_file_to_signed_url
      • create_snapshot
      • get_snapshot_status
      • simulate
      • gong_list_calls
      • gong_get_transcript
      • gong_get_call_details
      • fathom_list_meetings
      • fathom_get_transcript
      • fathom_get_meeting_details
      • fireflies_list_transcripts
      • fireflies_get_transcript
      • fireflies_search_transcripts
  • Direct API
    • Overview
    • Authentication
    • Error Handling
  • Core Concepts
    • Minds, Snapshots, & Simulations
    • SOC 2, HIPAA, & GDPR
LogoLogo
LogoLogo
On this page
  • Parameters
  • name
  • Request
  • Response
  • Response Properties
  • Mind Object
  • Digital Twin Object
  • Other Arrays
  • Error Responses
  • Next Steps
  • See Also
MCP ServerTools Reference

create_mind

Create a new digital mind entity
Was this page helpful?
Previous

get_signed_upload_url

Request a secure URL for file uploads
Next
Built with
CREATE

create_mind

Creates a new digital mind entity that represents a person’s communication patterns and decision-making style. This is the first step in the Mind Reasoner workflow.

Creating a mind establishes a digital identity that holds all training data and enables simulations. Once created, you can upload conversation data to train it and run unlimited simulations.

Parameters

name

Typestring
RequiredYes
DescriptionA descriptive name for the mind

Use clear, descriptive names that help you identify the mind later, such as “Sales Manager Alex” or “Customer Service Team”.

Request

1{
2 "name": "Customer Service Manager"
3}

Response

1{
2 "mind": {
3 "id": "123e4567-e89b-12d3-a456-426614174000",
4 "name": "Customer Service Manager",
5 "slug": "customer-service-manager",
6 "imageUrl": null,
7 "socialMedia": null,
8 "scope": "private",
9 "isSelf": false,
10 "tokenCount": null,
11 "organizationId": "123e4567-e89b-12d3-a456-426614174001",
12 "createdAt": "2025-01-01T00:00:00.000Z",
13 "updatedAt": "2025-01-01T00:00:00.000Z"
14 },
15 "digitalTwin": {
16 "id": "123e4567-e89b-12d3-a456-426614174002",
17 "name": "Default Twin",
18 "mindId": "123e4567-e89b-12d3-a456-426614174000",
19 "isDefault": true,
20 "createdAt": "2025-01-01T00:00:00.000Z",
21 "updatedAt": "2025-01-01T00:00:00.000Z"
22 },
23 "mindAssessments": [],
24 "mindCategories": []
25}

Response Properties

Returns a complete mind object with nested structures:

Mind Object

PropertyTypeDescription
mind.idstringRequired for all operations - Primary mind identifier
mind.namestringDescriptive name from request
mind.slugstringURL-friendly identifier
mind.imageUrlstring | nullOptional avatar URL
mind.socialMediaobject | nullOptional social media handles
mind.scopestringAccess level: private or public
mind.isSelfbooleanWhether this represents the account owner
mind.tokenCountnumber | nullTokens processed (null on creation)
mind.organizationIdstringOrganization identifier
mind.createdAtstringISO 8601 creation timestamp
mind.updatedAtstringISO 8601 last modified timestamp

Digital Twin Object

PropertyTypeDescription
digitalTwin.idstringRequired for snapshots - Digital twin identifier
digitalTwin.namestringName (typically “Default Twin”)
digitalTwin.mindIdstringReferences parent mind ID
digitalTwin.isDefaultbooleanWhether this is the default twin
digitalTwin.createdAtstringISO 8601 creation timestamp
digitalTwin.updatedAtstringISO 8601 last modified timestamp

Other Arrays

PropertyTypeDescription
mindAssessmentsarrayTraining snapshots (empty on creation)
mindCategoriesarrayOrganizational categories (empty on creation)

Save These IDs

Save both mind.id and digitalTwin.id from the response. You’ll need them for all subsequent operations. Your AI assistant handles this automatically, but when building custom integrations, store these in your application’s state or database.

Error Responses

401 Unauthorized
1{
2 "error": "Unauthorized",
3 "message": "Invalid or missing API key"
4}

Solution: Verify your API key in the MCP server configuration and ensure the format is correct: Bearer YOUR_KEY.

400 Bad Request
1{
2 "error": "Bad Request",
3 "message": "Name is required",
4 "details": {
5 "field": "name",
6 "issue": "missing"
7 }
8}

Solution: Ensure the name parameter is provided as a non-empty string.

429 Rate Limit Exceeded
1{
2 "error": "Too Many Requests",
3 "message": "Rate limit exceeded. Retry after 60 seconds",
4 "retryAfter": 60
5}

Solution: Wait for the time specified in retryAfter before making additional requests.

Next Steps

After creating a mind, continue with:

1

Get Upload URL

get_signed_upload_url - Request a secure upload URL

2

Upload File

upload_file_to_signed_url - Upload your transcript file

3

Create Snapshot

create_snapshot - Process the data into a trained model

See Also

Tools Reference

View all available MCP tools

MCP Quick Start

See the complete workflow in action