AI agents call memory_audit to retrieve information from Tages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The memory_audit tool only inspects and reports on existing project memory metrics and quality indicators. It generates no side effects—no data creation, modification, deletion, code execution, or financial operations. The tool simply analyzes stored context and provides diagnostic feedback, making it a pure Read operation with minimal risk.
From the tool's definition Tool performs auditing and analysis: "Audit project memory coverage and quality: type distribution, brief-critical coverage score, imperative phrasing ratio, and actionable suggestions." These are all read-only analytical operations that retrieve and evaluate…
Attacks that exploit this kind of access
Audit project memory coverage and quality: type distribution, brief-critical coverage score, imperative phrasing ratio, and actionable suggestions. It is categorised as a Read tool in the Tages MCP Server, which means it retrieves data without modifying state.
Register the Tages MCP server in PolicyLayer and add a rule for memory_audit: 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 Tages. Nothing to install.
memory_audit 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 memory_audit 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 memory_audit. 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.
memory_audit is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →