Cheap aggregate: counts of log lines by level + the top 10 distinct error/warning messages over a window. Use as a first pass before fleet_logs_recent.
AI agents call fleet_logs_summary to retrieve information from Fleet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes log data without modifying, deleting, or executing any operations. It is a diagnostic read operation with minimal blast radius if misused by an AI agent—worst case would be repeated queries consuming resources, but no state changes or destructive actions possible.
From the tool's definition Tool description states it provides 'counts of log lines by level + the top 10 distinct error/warning messages' - pure data retrieval with no modification, deletion, or side effects.
Documented attack patterns abuse exactly the kind of access fleet_logs_summary gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fleet, and nothing reaches the server without passing your rules. This is the rule we recommend for fleet_logs_summary:
{
"version": "1",
"default": "deny",
"tools": {
"fleet_logs_summary": {}
}
}fleet_logs_summary 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.
Cheap aggregate: counts of log lines by level + the top 10 distinct error/warning messages over a window. Use as a first pass before fleet_logs_recent. It is categorised as a Read tool in the Fleet MCP Server, which means it retrieves data without modifying state.
Register the Fleet MCP server in PolicyLayer and add a rule for fleet_logs_summary: 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 Fleet. Nothing to install.
fleet_logs_summary 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 fleet_logs_summary 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 fleet_logs_summary. 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.
fleet_logs_summary is provided by the Fleet MCP server (wrxck/fleet). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fleet, 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.
39 Fleet tools catalogued and risk-classified — across an index of 43,000+ MCP servers.