fetch_page_markdown
AI agents call fetch_page_markdown to retrieve information from Awesome Confluence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Confluence page content converted to Markdown format. It performs a query/fetch operation with no side effects—no data is created, modified, or deleted. The empty description slightly reduces confidence, but the name and server context clearly indicate a read-only retrieval operation. Severity is low as misuse would only result in accessing information.
From the tool's definition Tool name 'fetch_page_markdown' combined with server description stating it 'Supports listing, searching, and fetching pages.' The verb 'fetch' and context of retrieving page content in Markdown format indicates data retrieval without modification.
Attacks that exploit this kind of access
fetch_page_markdown. It is categorised as a Read tool in the Awesome Confluence MCP Server, which means it retrieves data without modifying state.
Register the Awesome Confluence MCP server in PolicyLayer and add a rule for fetch_page_markdown: 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 Awesome Confluence. Nothing to install.
fetch_page_markdown 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 fetch_page_markdown 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 fetch_page_markdown. 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.
fetch_page_markdown is provided by the Awesome Confluence MCP server (mazhar480/awesome-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 →