AI agents use jira_add_comment 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.
Adding a comment creates new data in Jira and is reversible (comments can be edited or deleted). This is a Write operation. Severity is medium because an agent could spam comments or post misleading information to issues, potentially disrupting team workflows, but the impact is limited to comment data and can be remediated.
From the tool's definition Tool name 'jira_add_comment' indicates adding/creating a comment; sibling tools like 'jira_create_issue' and 'confluence_add_comment' confirm the pattern of write operations on this server.
Attacks that exploit this kind of access
jira_add_comment. 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_add_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 Atlassian. Nothing to install.
jira_add_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 jira_add_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 jira_add_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.
jira_add_comment 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 →