get_page_images
AI agents call get_page_images to retrieve information from Confluence MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves images from Confluence pages without modifying or deleting data. It is a read-only query operation consistent with the server's stated purpose of 'extracting and converting' content for analysis. No side effects or destructive capability. Severity is low because unauthorized image access poses minimal risk compared to other threat categories.
From the tool's definition Tool named 'get_page_images' on a server described as 'reading and analyzing Confluence documentation content.' Sibling tools (get_child_pages, get_confluence_page, get_page_attachments, get_page_structure, search_in_page) are all retrieval operations.
Attacks that exploit this kind of access
get_page_images. It is categorised as a Read tool in the Confluence MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Confluence MCP Server MCP server in PolicyLayer and add a rule for get_page_images: 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 Confluence MCP Server. Nothing to install.
get_page_images 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_images 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_images. 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_images is provided by the Confluence MCP Server MCP server (onclicklistener2048/confluence-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 →