AI agents call get_confluence_pages 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.
The tool name strongly suggests querying or retrieving Confluence pages without modification. The description is empty, which lowers confidence slightly, but the naming convention is consistent with other read-only tools in the server. No side effects are expected from a 'get' operation. Severity is low as it merely retrieves data with no destructive or operational impact.
From the tool's definition Tool name 'get_confluence_pages' indicates retrieval of Confluence pages. Sibling tools follow naming patterns where 'get_*' tools are read-only (get_confluence_content, get_confluence_page_inline_comments, get_jira_issue) while 'create_*' and 'update_*' are…
Documented attack patterns abuse exactly the kind of access get_confluence_pages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Atlassian, and nothing reaches the server without passing your rules. This is the rule we recommend for get_confluence_pages:
{
"version": "1",
"default": "deny",
"tools": {
"get_confluence_pages": {}
}
}get_confluence_pages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_confluence_pages. 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_confluence_pages: 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_confluence_pages 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_confluence_pages 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_confluence_pages. 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_confluence_pages is provided by the MCP Atlassian MCP server (samwang0723/mcp-atlassian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Atlassian, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 MCP Atlassian tools catalogued and risk-classified — across an index of 43,000+ MCP servers.