> This page is for version v8.3.0 (default).
> For other versions, use one of these documentation indexes:
> - v8.3.0 (default): https://docs.workflows.com/v-8-3-0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.workflows.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.workflows.com/_mcp/server.

# Tools Reference

Mind Reasoner provides eight

MCP tools

that work together in a logical sequence. You don't need to memorize these tools—simply describe what you want in natural language, and Mind Reasoner will automatically select and execute the appropriate tools.

## Available Tools

| Tool                                                     | Operation | Purpose                 |
| -------------------------------------------------------- | --------- | ----------------------- |
| [get_all_minds](/mcp-tool-get-all-minds)                 | READ      | List all minds          |
| [search_minds](/mcp-tool-search-minds)                   | READ      | Search for minds        |
| [create_mind](/mcp-tool-create-mind)                     | CREATE    | Create digital entity   |
| [get_signed_upload_url](/mcp-tool-get-signed-upload-url) | GET       | Request upload URL      |
| [upload_file_to_signed_url](/mcp-tool-upload-file)       | UPLOAD    | Upload transcript file  |
| [create_snapshot](/mcp-tool-create-snapshot)             | CREATE    | Start AI training       |
| [get_snapshot_status](/mcp-tool-get-snapshot-status)     | GET       | Check training progress |
| [simulate](/mcp-tool-simulate)                           | RUN       | Run predictions         |

> **Note**
>
> **Most commonly used:** `get_all_minds`, `search_minds`, and `simulate` for working with existing minds. Setup tools are typically used once per mind.

## Integration Tools (Optional)

When you connect Gong, Fathom, or Fireflies to your MCP server, **up to 9 additional tools** become available alongside the core Mind Reasoner tools. These tools let you access existing transcript repositories without manual file uploads.

### Gong Tools (3)

| Tool                                                     | Purpose                                             |
| -------------------------------------------------------- | --------------------------------------------------- |
| [gong_list_calls](/mcp-tool-gong-list-calls)             | List sales call recordings with date filtering      |
| [gong_get_transcript](/mcp-tool-gong-get-transcript)     | Get detailed transcripts with speaker attribution   |
| [gong_get_call_details](/mcp-tool-gong-get-call-details) | Get participant details, topics, and call analytics |

### Fathom Tools (3)

| Tool                                                               | Purpose                                       |
| ------------------------------------------------------------------ | --------------------------------------------- |
| [fathom_list_meetings](/mcp-tool-fathom-list-meetings)             | List meetings with summaries and participants |
| [fathom_get_transcript](/mcp-tool-fathom-get-transcript)           | Get transcripts with speaker details          |
| [fathom_get_meeting_details](/mcp-tool-fathom-get-meeting-details) | Get comprehensive meeting information         |

### Fireflies Tools (3)

| Tool                                                                   | Purpose                                         |
| ---------------------------------------------------------------------- | ----------------------------------------------- |
| [fireflies_list_transcripts](/mcp-tool-fireflies-list-transcripts)     | List meeting transcripts with date filtering    |
| [fireflies_get_transcript](/mcp-tool-fireflies-get-transcript)         | Get detailed transcripts with speaker analytics |
| [fireflies_search_transcripts](/mcp-tool-fireflies-search-transcripts) | Search transcripts by keyword                   |

> **Graceful Degradation**
>
> Integration tools only appear when the corresponding credentials are configured. The MCP server works perfectly without any integrations—they're completely optional and additive.

**Learn more:**

* [Integration Overview](/mcp-integrations) - What integrations are available and why use them
* [Gong Setup](/mcp-integrations-gong-setup) - How to connect to Gong
* [Fathom Setup](/mcp-integrations-fathom-setup) - How to connect to Fathom
* [Fireflies Setup](/mcp-integrations-fireflies-setup) - How to connect to Fireflies

## Workflow

### Discovery Phase (Optional)

Explore existing minds before creating new ones:

```
get_all_minds or search_minds
   ↓ Returns: List of minds with IDs
```

### Setup Phase

Create and train new minds:

```
1. create_mind
   ↓ Returns: mindId, digitalTwinId

2. get_signed_upload_url
   ↓ Returns: signedUrl, artifactId

3. upload_file_to_signed_url
   ↓ Confirms upload

4. create_snapshot
   ↓ Returns: snapshotId

5. get_snapshot_status
   ↓ Waits for: status = "completed"

6. simulate
   ↓ Returns: AI predictions
```

> **Tip**
>
> Your AI assistant handles the workflow automatically. Understanding this sequence helps when debugging or building custom integrations.

## Workflow Phases

### Setup Phase

Create the

digital entity

and upload

conversation data

.

| Aspect        | Details                                                                                                                                            |
| ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Tools**     | [create_mind](/mcp-tool-create-mind), [get_signed_upload_url](/mcp-tool-get-signed-upload-url), [upload_file_to_signed_url](/mcp-tool-upload-file) |
| **Time**      | 2-5 minutes                                                                                                                                        |
| **Frequency** | Once per mind                                                                                                                                      |

### Training Phase

Process uploaded data into a

trained AI model

.

| Aspect        | Details                                                                                            |
| ------------- | -------------------------------------------------------------------------------------------------- |
| **Tools**     | [create_snapshot](/mcp-tool-create-snapshot), [get_snapshot_status](/mcp-tool-get-snapshot-status) |
| **Time**      | 5-15 minutes (asynchronous)                                                                        |
| **Frequency** | Once per dataset (or when updating)                                                                |

### Simulation Phase

Run unlimited predictions using the trained model.

| Aspect        | Details                        |
| ------------- | ------------------------------ |
| **Tools**     | [simulate](/mcp-tool-simulate) |
| **Time**      | Seconds per simulation         |
| **Frequency** | Unlimited                      |

## Common Patterns

### Discovering Existing Minds

Check what minds already exist before creating new ones.

**Time:** Seconds

**Natural language example:**

```
"Show me all minds I've created"
"Find minds related to sales"
"Do I already have a mind for Sarah?"
```

### First-Time Setup

Run the core workflow to create a mind, upload data, train the model, and run your first simulation.

**Time:** 10-20 minutes (mostly waiting for training)

**Natural language example:**

```
"Create a mind for my sales manager using the transcript
at /Documents/sales-calls.vtt, then simulate how they'd
handle pricing objections."
```

#### Setup

Create mind, get upload URL, upload transcript

#### Train

Create snapshot, wait for completion

#### Simulate

Run your first prediction

### Adding New Data

Update an existing mind by skipping step 1 (mind already exists) and running steps 2-6 with new data.

**Time:** 7-17 minutes

#### Upload

Get new upload URL, upload additional transcript

#### Retrain

Create new snapshot with updated data

#### Test

Run simulations with improved model

### Running Multiple Simulations

After training is complete, run `simulate` as many times as needed without re-training.

**Time:** Seconds per simulation

**Perfect for:**

* Testing multiple scenarios
* Training team members
* QA validation
* Batch predictions

## Error Handling

All tools return standard HTTP error responses. Each tool's documentation page includes detailed error handling guidance.

#### 401 Unauthorized

Invalid or missing API key. Verify key in MCP server configuration.

#### 404 Not Found

Resource ID is incorrect or deleted. Double-check IDs (case-sensitive).

#### 429 Rate Limit Exceeded

Too many requests. Wait for the time specified in `retryAfter` before retrying.

#### 400 Bad Request

Invalid parameters or format. Check the error `details` field for specifics.

## See Also

#### [MCP Quick Start](/mcp-quickstart)

Complete walkthrough from setup to simulation

#### [create_mind](/mcp-tool-create-mind)

Start here: Create your first digital mind

#### [simulate](/mcp-tool-simulate)

Most commonly used: Run AI simulations