AI agents call get_system_info 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 only reads and returns system information; it has no side effects, does not execute commands, does not modify data, and does not create obligations. It is a classic Read operation that gathers diagnostic data for inspection purposes. The server's safety model requiring 'explicit flags for mutating actions' further confirms this is a non-mutating query.
From the tool's definition Tool description states it retrieves 'OS, kernel, uptime, CPU/mem summary, load average' — purely informational system metrics with no modification or execution capabilities. The verb phrase 'One cheap call' reinforces it is a simple query operation.
Attacks that exploit this kind of access
OS, kernel, uptime, CPU/mem summary, load average. One cheap call. 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_system_info: 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_system_info 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_system_info 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_system_info. 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_system_info 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 →