AI agents call audit to retrieve information from Recall without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves an audit/provenance trail of past operations. It is a read-only query that returns historical records without modifying, executing, or deleting any data. Severity is low because it only reads audit metadata, though it could expose sensitive operational history.
From the tool's definition Return provenance trail of operations for a target id (or all)
Attacks that exploit this kind of access
Return provenance trail of operations for a target id (or all). It is categorised as a Read tool in the Recall MCP Server, which means it retrieves data without modifying state.
Register the Recall MCP server in PolicyLayer and add a rule for 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 Recall. Nothing to install.
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 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 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.
audit is provided by the Recall MCP server (yash194/recall). 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 →