confluence_get_content
AI agents call confluence_get_content to retrieve information from Inhouse Confluence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves content from Confluence without side effects. The naming convention and context of sibling tools, combined with the server's stated focus on retrieval and search operations, confirm this is a Read operation. The empty description reduces confidence slightly, but the consistent pattern across the tool family and server documentation provides strong evidence.
From the tool's definition Tool name prefix 'confluence_get_' indicates retrieval operation. Server description emphasizes 'search, content retrieval' as core functions.
Attacks that exploit this kind of access
confluence_get_content. It is categorised as a Read tool in the Inhouse Confluence MCP Server, which means it retrieves data without modifying state.
Register the Inhouse Confluence MCP server in PolicyLayer and add a rule for confluence_get_content: 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 Inhouse Confluence. Nothing to install.
confluence_get_content 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 confluence_get_content 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 confluence_get_content. 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.
confluence_get_content is provided by the Inhouse Confluence MCP server (janus-06/inhouse_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 →