AI agents call get_test_with_steps to retrieve information from Mxray without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves test information and steps from Xray Test Management without modifying, executing, deleting, or creating any data. It is a read-only query operation with minimal blast radius if misused by an AI agent—the worst outcome would be unauthorized disclosure of test information.
From the tool's definition Tool name 'get_test_with_steps' and description 'Get test details including test steps' indicate retrieval/query operations. The verb 'get' and phrase 'test details' confirm data retrieval with no modification.
Attacks that exploit this kind of access
Get test details including test steps from Xray (requires Xray credentials). It is categorised as a Read tool in the Mxray MCP Server, which means it retrieves data without modifying state.
Register the Mxray MCP server in PolicyLayer and add a rule for get_test_with_steps: 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 Mxray. Nothing to install.
get_test_with_steps 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_with_steps 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_with_steps. 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_with_steps is provided by the Mxray MCP server (mxray-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 →