AI agents use add_task_comment to create or update resources in Jira — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jira environment.
Adding a comment creates new data in Jira and modifies the task's state reversibly. While comments can be deleted, the add operation itself is a standard write action. Severity is medium because a compromised agent could spam tasks with unwanted comments or inject malicious information, but the impact is limited to comment data and doesn't affect critical system operations or financial data.
From the tool's definition Tool description states 'Add a markdown comment to a Jira task', which performs a create operation on task comments. This is a write action that modifies the task by adding new data.
Attacks that exploit this kind of access
Add a markdown comment to a Jira task. The markdown is automatically converted to ADF format. It is categorised as a Write tool in the Jira 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_task_comment: 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. Nothing to install.
add_task_comment 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_task_comment 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_task_comment. 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_task_comment is provided by the Jira MCP server (softspark/jira-mcp). 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 →