get_page_children
AI agents call get_page_children to retrieve information from MCP Atlassian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves child pages from a parent page in Confluence. Retrieval operations that query data without side effects are categorized as Read. The low severity reflects minimal blast radius—misuse would only expose information already accessible via normal Confluence permissions, not cause data loss or system damage.
From the tool's definition Tool name 'get_page_children' indicates a retrieval operation. The 'get_*' prefix is consistent with Read operations (get_issue, get_comments, get_agile_boards are sibling Read tools on the same server).
Attacks that exploit this kind of access
get_page_children. It is categorised as a Read tool in the MCP Atlassian MCP Server, which means it retrieves data without modifying state.
Register the MCP Atlassian MCP server in PolicyLayer and add a rule for get_page_children: 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 MCP Atlassian. Nothing to install.
get_page_children 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 get_page_children 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 get_page_children. 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.
get_page_children is provided by the MCP Atlassian MCP server (omkar9854/mcp-atlassian-onpremdc). 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 →