> ## Documentation Index
> Fetch the complete documentation index at: https://docs.stackone.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Flowise

> Connect StackOne MCP server to FlowiseAI for visual AI agent workflows with access to all StackOne integrations.

## Overview

[FlowiseAI](https://flowiseai.com/) is a visual workflow builder for AI agents with native MCP support.

## Prerequisites

* Flowise installed ([installation guide](https://docs.flowiseai.com/))
* A StackOne linked account ([set one up here](/embed/account-linking/auth-link))

## Setup

<Steps>
  <Step title="Get your MCP URL from the dashboard">
    1. Go to **Connectors** in the left nav and open the connector you want to use
    2. Click **Use in Agent** in the top right
    3. On the **Use** tab, click **MCP Server** under "Use with Agent Client"
    4. Select a linked account from the dropdown
    5. Choose **HTTPS MCP** as the client
    6. Copy the generated URL — it looks like:
       ```
       https://api.stackone.com/mcp?token=<session_token>
       ```

    The token encodes your account identity. No separate API key or account ID header is needed.

    <Tip>
      The token expires after one year. Regenerate it at any time using the refresh button in the MCP tile.
    </Tip>
  </Step>

  <Step title="Add MCP Server to Flowise">
    Navigate to your Flowise instance and open the chatflow where you want to add StackOne tools.

    1. In the left sidebar, find **"Custom MCP"** in the **"Tools"** section
    2. Drag the **Custom MCP** component onto your canvas and connect it to your agent
    3. In the MCP Server Config, add:

    ```json theme={null}
    {
      "url": "https://api.stackone.com/mcp?token=<session_token>"
    }
    ```

    Replace `<session_token>` with the token from the previous step.
  </Step>

  <Step title="Configure available tools">
    Once connected, Flowise discovers all available StackOne tools for the account. Use the tool filter to search by provider or action type and enable only what your workflow needs.
  </Step>
</Steps>

***

## Advanced: manual API key setup

If you prefer to authenticate with your API key and account ID directly:

```json theme={null}
{
  "url": "https://api.stackone.com/mcp",
  "headers": {
    "Authorization": "Basic <YOUR_BASE64_TOKEN>",
    "x-account-id": "<YOUR_ACCOUNT_ID>"
  }
}
```

To generate the base64 token:

```bash theme={null}
echo -n "<stackone_api_key>:" | base64
```

See [Authentication & Security](/embed/call-actions/mcp#calling-actions) for details.

***

## Limitations

* **Transport:** StackOne only supports HTTP transport (no STDIO or SSE)
* **Tool Discovery:** Tools are determined by the enabled actions for the integration configuration associated with the linked account

***

## Handling large tool catalogs

If the connector exposes many actions, add the `tool-mode=search_execute` query parameter to the MCP URL in your config. The client then registers just two tools — search + execute — and the agent discovers actions at runtime, so the context footprint stays flat however large the catalog:

```
https://api.stackone.com/mcp?tool-mode=search_execute
```

For a token URL, append it as an extra parameter: `https://api.stackone.com/mcp?token=<session_token>&tool-mode=search_execute`.

See [Tool Discovery](/features/tool-discovery) for how search works, its accuracy, and the other modes.

## Optimize and secure

With your agent connected, use StackOne's platform features to optimize performance and secure every call.

<CardGroup cols={3}>
  <Card title="Search & Execute" icon="magnifying-glass" href="/optimize/search-and-execute">
    Reduce context and save tokens.
  </Card>

  <Card title="Data Sync" icon="arrows-rotate" href="/optimize/data-sync">
    Reduce latency and enable semantic search.
  </Card>

  <Card title="Defender" icon="shield-halved" href="/secure/defender">
    Block prompt injections before they reach your agent.
  </Card>
</CardGroup>