Skip to main content
The AI Playground lets you test any action from your linked accounts using natural language.
Playground Main Interface
Testing tool, not a production agent. The Playground is designed for quickly testing actions and exploring capabilities. For production use cases, build your own agent using our MCP Server, AI Toolset, or A2A Protocol. See Agent Protocols Comparison for guidance.
Access Required: Contact StackOne support if you don’t see the Playground in your dashboard.

​
Getting Started

1

Select accounts

Click Manage Action Sources and select one or more linked accounts.
2

Configure actions (optional)

Expand the Actions section to enable/disable specific actions before chatting.
3

Start chatting

Ask questions like “List 5 employees” or “What tools can I use?”
You can change action selection mid-conversation — updates take effect on the next message.

​
Example Queries

The queries you can run depend on which accounts you’ve connected and what actions are available. Tailor your prompts to your agent’s use case:
Start with “What tools can I use?” to see available actions for your selected accounts.

​
Model Selection

Click the model selector at the bottom right to switch between models:
StackOne Tool Calling Model (Beta)StackOne is fine-tuning a specialized model optimized for SaaS tool calling, at lower cost than leading models.Contact ai@stackone.com to join the beta.

​
Defender

The Playground includes a StackOne Defender toggle in the configuration sidebar that scans tool call responses for prompt injection attempts before the model sees them. Per-request override. The Playground toggle is a per-request override — it controls Defender for the Playground session only, regardless of what the project-level setting is. Use it to test how your agent behaves with Defender on or off without changing your project configuration. The toggle defaults to on in the Playground. Risk indicators on tool calls. When Defender is enabled, every tool call in the chat log displays a colored icon next to its status badge: Hover any icon for the precise risk level reported by Defender. Behaviour when blocked. With Block High Risk Content enabled at the project level, a high/critical tool call surfaces as a Blocked status in the chat log and the model receives an error in place of the tool response. The agent can react like any other tool error — retry, skip, or surface to the user. For the full Defender configuration reference — detection modes, thresholds, large-response behaviour, SFE, and SDK overrides — see the Defender guide.

​
Use Setup

The “Use Setup” button shows configuration for connecting StackOne’s MCP server to your own applications:
Use Setup Dialog
  • URL: https://api.stackone.com/mcp
  • Auth: Basic <base64-encoded-api-key>
  • Header: x-account-id: <your-account-id>
For full setup instructions, see the MCP Quickstart. To understand which protocol is right for your use case, see Agent Protocols Comparison.

​
Troubleshooting

Ensure accounts are linked in the Accounts section and actions are enabled in your connector configuration.
Switch to Haiku (fastest) or reduce the number of selected accounts.
Verify the action is enabled in your integration configuration. Check Request Logs for details.

Defender

Prompt-injection defense for tool call responses

Agent Protocols

Choose the right protocol for production

MCP Quickstart

Connect MCP clients