Bounded grep across recent container logs. Returns matching lines with 0 lines of context, capped at max_results. Cheaper than fleet_logs_recent + manual filtering.
AI agents call fleet_logs_search 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 searches container logs without modifying, deleting, or executing operations. It performs a bounded grep query with capped results, which is a pure read operation. The low severity reflects that log data access poses minimal risk compared to tools that deploy applications, delete data, or execute arbitrary commands.
From the tool's definition Tool description states it performs 'Bounded grep across recent container logs' and 'Returns matching lines' — these are retrieval operations with no side effects.
Documented attack patterns abuse exactly the kind of access fleet_logs_search 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_search:
{
"version": "1",
"default": "deny",
"tools": {
"fleet_logs_search": {}
}
}fleet_logs_search 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.
Bounded grep across recent container logs. Returns matching lines with 0 lines of context, capped at max_results. Cheaper than fleet_logs_recent + manual filtering. 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_search: 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_search 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_search 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_search. 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_search 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.