AI agents use create_test_result to create or update resources in Mcp Jama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Jama environment.
The tool modifies test result records reversibly—status values can be changed or corrected later. This is Write category (creates/modifies data reversibly) rather than Destructive (no deletion/overwriting). Severity is medium because misuse could corrupt test data integrity and reporting, but effects are limited to test management context within a project.
From the tool's definition Tool description states it records results to a test run (テストランに結果を記録する), modifying test execution status with values like PASSED/FAILED/BLOCKED/NOT_RUN/INPROGRESS. This creates/updates test result data within JAMA Cloud.
Attacks that exploit this kind of access
テストランに結果を記録する。status は PASSED/FAILED/BLOCKED/NOT_RUN/INPROGRESS のいずれか。. It is categorised as a Write tool in the Mcp Jama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Jama MCP server in PolicyLayer and add a rule for create_test_result: 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 Mcp Jama. Nothing to install.
create_test_result 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_result 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_result. 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_result is provided by the Mcp Jama MCP server (keisukeshima/mcp-jama). 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 →