AI agents use create_test to create or update resources in Mxray — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mxray environment.
This tool creates new test objects in Jira Cloud, which is a reversible data modification operation. It does not execute arbitrary code, delete data, or trigger financial transactions. While it modifies state, the creation of test entities in a test management system is a standard write operation with medium severity given the potential for test data accumulation or organizational disruption if abused at scale.
From the tool's definition The tool description explicitly states 'Create a new test' which involves creating data in Jira. The verb 'create' combined with the noun 'test' clearly indicates a write operation that adds a new resource to the system.
Attacks that exploit this kind of access
Create a new test in Jira with specified type (Manual/Cucumber/Generic). It is categorised as a Write tool in the Mxray MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mxray MCP server in PolicyLayer and add a rule for create_test: 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.
create_test 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 create_test 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 create_test. 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.
create_test 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 →