AI agents call listProcesses to retrieve information from Shell MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns data about system state without modifying, deleting, or executing anything. However, it reveals sensitive information about system processes that could be leveraged for reconnaissance in a compromised environment, justifying medium severity rather than low. The confidence is high because the intent is unambiguous.
From the tool's definition listProcesses retrieves information about running processes on the host system; no side effects or modifications occur. The description confirms it 'List[s] running processes' which is a data retrieval operation.
Attacks that exploit this kind of access
List running processes on the host system using. It is categorised as a Read tool in the Shell MCP MCP Server, which means it retrieves data without modifying state.
Register the Shell MCP server in PolicyLayer and add a rule for listProcesses: 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 Shell MCP. Nothing to install.
listProcesses 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 listProcesses 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 listProcesses. 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.
listProcesses is provided by the Shell MCP server (lucivuc/shell-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 →