AI agents use jira_create_issue to create or update resources in Atlassian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Atlassian environment.
Creating a Jira issue is a reversible write operation that adds data to the system. It does not execute arbitrary code, delete data irreversibly, or move money. The severity is medium because creating unwanted issues could spam a project or consume resources, but the impact is limited in scope and can be undone (issues can be closed or deleted).
From the tool's definition Tool name 'jira_create_issue' indicates creation of a new Jira issue; server description confirms it enables LLMs to 'write...and manage issues'; sibling tools like 'jira_add_comment' and 'jira_delete_comment' confirm this server manages Jira workflow.
Attacks that exploit this kind of access
jira_create_issue. It is categorised as a Write tool in the Atlassian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Atlassian MCP server in PolicyLayer and add a rule for jira_create_issue: 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 Atlassian. Nothing to install.
jira_create_issue 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 jira_create_issue 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 jira_create_issue. 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.
jira_create_issue is provided by the Atlassian MCP server (tingyiy/atlassian-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 →