AI agents call query_container_stats to retrieve information from Beszel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that retrieves container performance metrics. It has no side effects, does not execute code or commands, and does not modify any data. The blast radius of misuse is minimal—an attacker could only gain visibility into container performance patterns, not control systems or access sensitive operations.
From the tool's definition Tool description states it 'Query[s] time-series statistics for a specific container (CPU, memory, network)' — purely retrieves monitoring data with no modification or execution capability.
Attacks that exploit this kind of access
Query time-series statistics for a specific container (CPU, memory, network). It is categorised as a Read tool in the Beszel MCP Server, which means it retrieves data without modifying state.
Register the Beszel MCP server in PolicyLayer and add a rule for query_container_stats: 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 Beszel. Nothing to install.
query_container_stats 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_container_stats 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_container_stats. 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_container_stats is provided by the Beszel MCP server (weeebdev/beszel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →