AI agents use import_testng_results to create or update resources in Xray MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xray MCP environment.
This tool creates new test execution records and modifies existing test status data, which are reversible write operations. It does not delete data (not Destructive), does not move money (not Financial), does not execute arbitrary code in environments outside Xray (not Execute), and is not purely informational (not Read).
From the tool's definition Tool description states it 'Automatically creates test execution and updates test statuses' - both write operations that modify data in Xray Test Management. The tool ingests TestNG XML results and persists changes to test execution records and status fields.
Attacks that exploit this kind of access
Import TestNG XML test results to Xray. Automatically creates test execution and updates test statuses. It is categorised as a Write tool in the Xray MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xray MCP server in PolicyLayer and add a rule for import_testng_results: 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 Xray MCP. Nothing to install.
import_testng_results is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the import_testng_results 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 import_testng_results. 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.
import_testng_results is provided by the Xray MCP server (korfu/mcp-xray). 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 →