Generate an audit report for a session showing all files read/written, commands executed, MCP tools used, and URLs fetched.
AI agents call audit_session to retrieve information from Claude Code Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
audit_session queries and retrieves historical session metadata (files accessed, commands run, tools used, URLs fetched) for reporting purposes. This is a read-only diagnostic operation with no side effects on the system or data. The low severity reflects minimal blast radius: misuse would only expose audit information, not alter or destroy systems.
From the tool's definition Tool description states it 'Generate[s] an audit report' that 'show[s]' (displays/retrieves) historical session data. No modifications, deletions, or external operations are performed—it is purely observational and introspective.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access audit_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for audit_session:
{
"version": "1",
"default": "deny",
"tools": {
"audit_session": {}
}
}audit_session 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.
Generate an audit report for a session showing all files read/written, commands executed, MCP tools used, and URLs fetched. It is categorised as a Read tool in the Claude Code Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Claude Code Toolkit MCP server in PolicyLayer and add a rule for audit_session: 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 Claude Code Toolkit. Nothing to install.
audit_session 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_session 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_session. 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_session is provided by the Claude Code Toolkit MCP server (asifkibria/claude-code-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code Toolkit, 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.
40 Claude Code Toolkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.