AI agents use katalon_create_test_case to create or update resources in Katalon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Katalon environment.
This tool creates new test case resources in Katalon Studio, which is a reversible write operation (test cases can be deleted or modified). It does not execute code, delete data irreversibly, or move money. While it could indirectly affect test execution workflows if maliciously crafted test cases are created, the primary action is data creation.
From the tool's definition Tool name contains 'create' and description states 'Create a new test case'; creates new test artifacts reversibly within Katalon Studio
Attacks that exploit this kind of access
Create a new test case with intelligent object identification. It is categorised as a Write tool in the Katalon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Katalon MCP server in PolicyLayer and add a rule for katalon_create_test_case: 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 Katalon. Nothing to install.
katalon_create_test_case 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 katalon_create_test_case 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 katalon_create_test_case. 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.
katalon_create_test_case is provided by the Katalon MCP server (pareshsoni468/katalon-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 →