mcp_audit_log
Read recent MCP write, runtime, dry-run, denied, and destructive tool audit events for the authenticated account.
This record as markdown: /tools/io-github-proagentstore-platform/mcp-audit-log.md
What mcp_audit_log does on ProAgentStore
AI agents call mcp_audit_log to retrieve information from ProAgentStore without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why mcp_audit_log is rated Low
The tool retrieves/queries audit log data for the authenticated account. Despite the audit log containing records of destructive or sensitive operations, the tool itself only reads and returns existing log entries without modifying, executing, or deleting anything. Severity is low as it only surfaces audit data, though it could expose sensitive operational information.
From the tool's definition Read recent MCP write, runtime, dry-run, denied, and destructive tool audit events
Attacks that exploit this kind of access
The rule that runs mcp_audit_log safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ProAgentStore, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mcp_audit_log, this is the rule to start with:
mcp_audit_log is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ProAgentStore, apply this rule, and every mcp_audit_log call is checked against it from then on.
Questions about mcp_audit_log
Read recent MCP write, runtime, dry-run, denied, and destructive tool audit events for the authenticated account. It is categorised as a Read tool in the ProAgentStore MCP Server, which means it retrieves data without modifying state.
Register the ProAgentStore MCP server in PolicyLayer and add a rule for mcp_audit_log: 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 ProAgentStore. Nothing to install.
mcp_audit_log 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 mcp_audit_log 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 mcp_audit_log. 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.
mcp_audit_log is provided by the ProAgentStore MCP server (https://mcp.proagentstore.online/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ProAgentStore, and thousands of servers like it.
This server
Across the catalogue