AI agents call get_process_top to retrieve information from Sysprobe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about running processes sorted by resource consumption (CPU or memory). It has no side effects, performs no mutations, executes no code, and does not delete or create anything. It is purely informational, making it a Read category risk with low severity—useful for diagnostics but harmless if misused by an AI agent.
From the tool's definition Tool description states 'Top resource-consuming processes' with sorting options—this is a query/retrieval operation that reads system process information without modifying state. The name 'get_process_top' further indicates a read-only retrieval action.
Attacks that exploit this kind of access
Top resource-consuming processes (sort_by 'cpu' or 'memory'). It is categorised as a Read tool in the Sysprobe MCP Server, which means it retrieves data without modifying state.
Register the Sysprobe MCP server in PolicyLayer and add a rule for get_process_top: 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 Sysprobe. Nothing to install.
get_process_top 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 get_process_top 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 get_process_top. 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.
get_process_top is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →