Query audit events for an app — authentication, admin mutations, and function invocations. Returns a unified event stream. Each event has: category 'auth' | 'admin' | 'function' event_type e.g. 'login', 'schema.apply', 'function.deploy', 'function.invoke' action 'create' | 'update' | 'delete' | '...
Risk signalsHigh parameter count (12 properties) · Admin/system-level operation
Part of the Mcp server.
Free to start. No card required.
AI agents call query_audit_logs to retrieve information from Mcp without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though query_audit_logs only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"query_audit_logs": {}
}
}See the full Mcp policy for all 47 tools.
These attack patterns abuse exactly the kind of access query_audit_logs gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Query audit events for an app — authentication, admin mutations, and function invocations. Returns a unified event stream. Each event has: category 'auth' | 'admin' | 'function' event_type e.g. 'login', 'schema.apply', 'function.deploy', 'function.invoke' action 'create' | 'update' | 'delete' | 'invoke' | 'enable' | 'disable' | null resource_type which resource the event acted on resource_id the resource identifier (function name, policy name, deployment id, etc.) actor_type 'platform_user' | 'app_user' | 'api_key' | 'system' | 'anonymous' actor_id platform user id / app user id / api key id event_data event-specific payload success whether the event succeeded correlation_id request id (ties related events together) Use this to: - Investigate who did what and when - Debug failing auth / admin / function flows - Monitor suspicious activity - Trace a request across subsystems via correlation_id Common filters: - category='admin' to see only administrative mutations - resource_type='function' + resource_id='my-fn' to see one function's history - actor_id=<user-id> to see one actor's activity - from / to to narrow to a time window Idempotency: Safe to call anytime (read-only). Historical auth events predating migration 034 are included (normalized).. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for query_audit_logs: 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 Mcp. Nothing to install.
query_audit_logs 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 query_audit_logs 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 query_audit_logs. 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.
query_audit_logs is provided by the MCP server (@butterbase/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 47 Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.