AI agents call session_list to retrieve information from Mcpx 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 existing sessions (size, age, idle time, byte counters) with no side effects, data modification, code execution, or destructive capability. It is a straightforward monitoring/audit function. The low severity reflects that session metadata leakage is a minor information disclosure relative to the destructive and execute capabilities present on the same server.
From the tool's definition Tool name 'session_list' and description 'List active sessions with size, age, idle, and byte counters' indicate a read-only query operation that retrieves metadata about active sessions without modifying or executing anything.
Attacks that exploit this kind of access
List active sessions with size, age, idle, and byte counters. It is categorised as a Read tool in the Mcpx MCP Server, which means it retrieves data without modifying state.
Register the Mcpx MCP server in PolicyLayer and add a rule for session_list: 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 Mcpx. Nothing to install.
session_list 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 session_list 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 session_list. 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.
session_list is provided by the Mcpx MCP server (rmednitzer/relay-shell). 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 →