AI agents call session_recv 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.
session_recv retrieves output that has already been produced by a shell session. It does not execute commands, modify data, delete data, or move money. The timeout parameter merely controls how long the read operation waits before returning; it does not change the fundamental nature of the action as a passive read operation.
From the tool's definition Tool description states 'Read buffered/new output from a session' — the verb 'read' and the action of retrieving already-generated output from a buffer indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Read buffered/new output from a session, waiting up to timeout seconds. 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_recv: 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_recv 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_recv 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_recv. 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_recv 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 →