AI agents call inspect_process_io 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 queries process state and relationships (open file descriptors, network sockets) to provide visibility into system diagnostics. It retrieves existing data without side effects. The low severity reflects that process inspection data is typically available to the user already and does not enable harmful actions on its own.
From the tool's definition Tool opens (inspects) and retrieves information about files and network connections held by a process. Uses verb 'Open' in the sense of examining/reading, with purpose stated as 'debug hangs' indicating diagnostic, non-mutating intent.
Attacks that exploit this kind of access
Open files & network connections held by a process (debug hangs). 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 inspect_process_io: 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.
inspect_process_io 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 inspect_process_io 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 inspect_process_io. 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.
inspect_process_io 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 →