AI agents call check_resources to retrieve information from Jlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries current system resource metrics (CPU, memory, GPU usage) and returns that information without side effects. It is purely informational and matches the 'Read' category definition of retrieving or querying data with no side effects. The low severity reflects that misuse would only expose resource information, not enable destructive or harmful actions.
From the tool's definition Tool name 'check_resources' and description 'Check compute resource usage: CPU, memory, and GPU' indicate a monitoring/query operation that retrieves resource status information without modifying any state.
Attacks that exploit this kind of access
Check compute resource usage: CPU, memory, and GPU. It is categorised as a Read tool in the Jlab MCP Server, which means it retrieves data without modifying state.
Register the Jlab MCP server in PolicyLayer and add a rule for check_resources: 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 Jlab. Nothing to install.
check_resources 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 check_resources 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 check_resources. 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.
check_resources is provided by the Jlab MCP server (kdkyum/jlab-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 →