AI agents call get_test_suite_format to retrieve information from Sentinel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns reference documentation about the YAML format structure needed for test suites. It has no side effects, does not modify or execute anything, and poses no security risk. It is a simple reference/query operation that helps users understand the expected input format.
From the tool's definition Tool name is 'get_test_suite_format' and description states 'Get the required YAML format' and 'understand how to write or generate test suites' — purely informational, retrieves documentation/schema.
Attacks that exploit this kind of access
Get the required YAML format of the API test suite. Use this to understand how to write or generate test suites for sentinel-mcp. It is categorised as a Read tool in the Sentinel MCP Server, which means it retrieves data without modifying state.
Register the Sentinel MCP server in PolicyLayer and add a rule for get_test_suite_format: 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 Sentinel. Nothing to install.
get_test_suite_format 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 get_test_suite_format 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 get_test_suite_format. 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.
get_test_suite_format is provided by the Sentinel MCP server (kal72/sentinel-mcp). 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 →