AI agents call testmo_search_cases_recursive to retrieve information from Testmo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve data without side effects or modifications. Recursive search through test cases is a query operation that fits the Read category. Even though the description is empty, the name strongly indicates a retrieval action.
From the tool's definition Tool name 'testmo_search_cases_recursive' indicates a search operation that recursively queries test cases. The verb 'search' and the absence of any modification keywords (create, update, delete, etc.) suggest a read-only retrieval function.
Attacks that exploit this kind of access
testmo_search_cases_recursive. It is categorised as a Read tool in the Testmo MCP Server, which means it retrieves data without modifying state.
Register the Testmo MCP server in PolicyLayer and add a rule for testmo_search_cases_recursive: 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 Testmo. Nothing to install.
testmo_search_cases_recursive 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 testmo_search_cases_recursive 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 testmo_search_cases_recursive. 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.
testmo_search_cases_recursive is provided by the Testmo MCP server (strelec00/testmo-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 →