AI agents call ps to retrieve information from Claude C2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves process information from remote systems, which is a Read operation. However, the severity is elevated to medium rather than low because: (1) process listings can reveal sensitive information about running services, credentials in command-line arguments, or internal system architecture; (2) it operates on remote systems across multiple platforms via an AI agent, creating potential for…
From the tool's definition Tool name 'ps' and description 'List processes. Auto-selects client.' indicate querying/retrieving process information without modifying system state.
Attacks that exploit this kind of access
List processes. Auto-selects client. It is categorised as a Read tool in the Claude C2 MCP Server, which means it retrieves data without modifying state.
Register the Claude C2 MCP server in PolicyLayer and add a rule for ps: 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 Claude C2. Nothing to install.
ps 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 ps 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 ps. 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.
ps is provided by the Claude C2 MCP server (0xyg3n/claude-c2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ps is one line of Claude C2's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →