AI agents use execute_test to create or update resources in JIRA Zephyr MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JIRA Zephyr MCP Server environment.
The tool writes/updates test execution results in Zephyr, which is a reversible data modification. It does not delete data, run code, or involve financial transactions. Severity is medium because misuse could corrupt test result records and affect reporting integrity, but the blast radius is limited to test management data.
From the tool's definition 'Update test execution results' — the tool modifies existing test execution records with new result data
Documented attack patterns abuse exactly the kind of access execute_test gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and JIRA Zephyr MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_test:
{
"version": "1",
"default": "deny",
"tools": {
"execute_test": {
"limits": [
{
"counter": "execute_test_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}execute_test stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update test execution results. It is categorised as a Write tool in the JIRA Zephyr MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the JIRA Zephyr MCP Server MCP server in PolicyLayer and add a rule for execute_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 JIRA Zephyr MCP Server. Nothing to install.
execute_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 execute_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 execute_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.
execute_test is provided by the JIRA Zephyr MCP Server MCP server (leorosignoli/jira-zephyr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from JIRA Zephyr MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 JIRA Zephyr MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.