AI agents use create_test_plan 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.
This tool creates a new test plan resource within JIRA Zephyr, which is a reversible write operation. It does not execute tests, delete data, or move financial resources. The blast radius is moderate because a malicious agent could create numerous test plans to pollute the system or cause organizational confusion, but the operation itself can be undone by deletion or modification.
From the tool's definition Tool name is 'create_test_plan' and description states 'Create a new test plan in Zephyr'. The verb 'create' indicates a write operation that produces a new persistent resource.
Documented attack patterns abuse exactly the kind of access create_test_plan 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 create_test_plan:
{
"version": "1",
"default": "deny",
"tools": {
"create_test_plan": {
"limits": [
{
"counter": "create_test_plan_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create_test_plan 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.
Create a new test plan in Zephyr. 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 create_test_plan: 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.
create_test_plan 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_plan 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_plan. 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_plan 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.