Get replies to a Confluence comment
AI agents call getConfluenceCommentChildren to retrieve information from Atlassian Multi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing data (comment replies) from Confluence without creating, modifying, or deleting anything. It is a straightforward query operation that poses minimal security risk even if invoked by an AI agent.
From the tool's definition Tool name contains 'get' and description states 'Get replies to a Confluence comment' — a pure retrieval operation with no side effects or modifications.
Attacks that exploit this kind of access
Get replies to a Confluence comment. It is categorised as a Read tool in the Atlassian Multi MCP Server, which means it retrieves data without modifying state.
Register the Atlassian Multi MCP server in PolicyLayer and add a rule for getConfluenceCommentChildren: 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 Multi. Nothing to install.
getConfluenceCommentChildren is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the getConfluenceCommentChildren 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 getConfluenceCommentChildren. 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.
getConfluenceCommentChildren is provided by the Atlassian Multi MCP server (ntlongctt/atlassian-multi-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 →