audit_log
Query the on-device audit log of tool calls. Reads JSONL rows from ~/.airmcp/audit.jsonl (+ rotated siblings)
This record as markdown: /tools/io-github-heznpc-iconnect/audit-log.md
What audit_log does on Iconnect
AI agents call audit_log to retrieve information from Iconnect without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why audit_log is rated Low
This tool retrieves and queries historical audit log data from local JSONL files without modifying, deleting, or executing code. It is a pure Read operation. Severity is medium rather than low because audit logs may contain sensitive information about user activities, credentials, or system state that could be exposed if an AI agent queries it without authorization, though the tool itself is read-only and poses no…
From the tool's definition Tool name 'audit_log' and description explicitly states 'Query the on-device audit log' and 'Reads JSONL rows from' a local file. The verb 'Query' and 'Reads' confirm read-only retrieval.
Attacks that exploit this kind of access
The rule that runs audit_log safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Iconnect, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For audit_log, this is the rule to start with:
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 Iconnect, apply this rule, and every audit_log call is checked against it from then on.
Questions about audit_log
Query the on-device audit log of tool calls. Reads JSONL rows from ~/.airmcp/audit.jsonl (+ rotated siblings). It is categorised as a Read tool in the Iconnect MCP Server, which means it retrieves data without modifying state.
Register the Iconnect MCP server in PolicyLayer and add a rule for 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 Iconnect. Nothing to install.
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 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 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.
audit_log is provided by the Iconnect MCP server (iconnect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Iconnect, and thousands of servers like it.
This server
Across the catalogue