AI agents use API-v1_0_create-autopilot-tasks to create or update resources in Magicpod — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Magicpod environment.
This tool creates or modifies test automation tasks within MagicPod, which are reversible operations. It falls under Write category rather than Execute because it creates task configuration objects rather than immediately executing test runs.
From the tool's definition Tool name and description indicate creation of Autopilot tasks: 'Create Autopilot tasks for test case creation and/or editing.' The verb 'Create' and explicit reference to task creation shows data modification without deletion.
Attacks that exploit this kind of access
Create Autopilot tasks for test case creation and/or editing. It is categorised as a Write tool in the Magicpod MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Magicpod MCP server in PolicyLayer and add a rule for API-v1_0_create-autopilot-tasks: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Magicpod. Nothing to install.
API-v1_0_create-autopilot-tasks is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the API-v1_0_create-autopilot-tasks rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for API-v1_0_create-autopilot-tasks. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
API-v1_0_create-autopilot-tasks is provided by the Magicpod MCP server (magic-pod/magicpod-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →