AI agents call search_test_cases to retrieve information from Tuskr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches test case information based on text criteria. It does not create, modify, delete, or execute operations on test cases or external systems. The optional 'automated_filter' parameter is a query constraint, not an action that triggers external effects. Search operations are read-only with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'search_test_cases' and description 'Search test-cases by key/title/steps text' indicate a query/search operation with no side effects.
Attacks that exploit this kind of access
Search test-cases by key/title/steps text; optional automated_filter. It is categorised as a Read tool in the Tuskr MCP Server, which means it retrieves data without modifying state.
Register the Tuskr MCP server in PolicyLayer and add a rule for search_test_cases: 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 Tuskr. Nothing to install.
search_test_cases 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 search_test_cases 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 search_test_cases. 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.
search_test_cases is provided by the Tuskr MCP server (zapkid/tuskr-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 →