AI agents call API-v1_0_list-test-settings to retrieve information from Magicpod without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns test settings data without any side effects. It is a data retrieval operation that poses minimal risk if misused by an AI agent, as it cannot modify, delete, or execute actions. The blast radius is limited to information disclosure of non-sensitive configuration metadata.
From the tool's definition Tool name includes 'list' and description states 'Retrieve available test settings' — classic read operation with no modification or execution.
Attacks that exploit this kind of access
Retrieve available test settings for a project. It is categorised as a Read tool in the Magicpod MCP Server, which means it retrieves data without modifying state.
Register the Magicpod MCP server in PolicyLayer and add a rule for API-v1_0_list-test-settings: 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_list-test-settings is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the API-v1_0_list-test-settings 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_list-test-settings. 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_list-test-settings 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 →