Add test steps to a test ticket via Zephyr integration
AI agents use add-test-steps to create or update resources in JIRA MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JIRA MCP environment.
This tool creates or modifies test step data in JIRA (reversibly), making it a Write operation rather than a destructive one. The severity is medium because modifying test steps could affect test execution and coverage tracking, but changes can be undone. Confidence is high (0.85) because the action is clearly stated as adding/creating data, though the description lacks details on scope or permissions implications.
From the tool's definition The tool description explicitly states it will 'Add test steps to a test ticket', which is a create/modify operation on existing test data within JIRA's Zephyr test management system.
Documented attack patterns abuse exactly the kind of access add-test-steps gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and JIRA MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add-test-steps:
{
"version": "1",
"default": "deny",
"tools": {
"add-test-steps": {
"limits": [
{
"counter": "add-test-steps_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add-test-steps 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.
Add test steps to a test ticket via Zephyr integration. It is categorised as a Write tool in the JIRA MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the JIRA MCP server in PolicyLayer and add a rule for add-test-steps: 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 MCP. Nothing to install.
add-test-steps 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 add-test-steps 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 add-test-steps. 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.
add-test-steps is provided by the JIRA MCP server (mankowskinick/jira-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from JIRA MCP, 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.
14 JIRA MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.