Get test case keys from a test run
AI agents call get_test_run_cases to retrieve information from Zephyr Scale MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves test case keys associated with a test run. It performs a read-only operation against the Zephyr Scale API without creating, modifying, deleting, or executing any actions. The low severity reflects minimal risk if misused by an AI agent—it can only expose existing test case metadata within the Jira project's test management system.
From the tool's definition Tool name 'get_test_run_cases' and description 'Get test case keys from a test run' both indicate a retrieval operation with no modification or execution of external effects.
Attacks that exploit this kind of access
Get test case keys from a test run. It is categorised as a Read tool in the Zephyr Scale MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zephyr Scale MCP Server MCP server in PolicyLayer and add a rule for get_test_run_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 Zephyr Scale MCP Server. Nothing to install.
get_test_run_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 get_test_run_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 get_test_run_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.
get_test_run_cases is provided by the Zephyr Scale MCP Server MCP server (milo0821/zephyr_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 →