Retrieve latest output from a terminal session.
AI agents call termf_live_output to retrieve information from TermPipe MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/queries existing terminal output with no side effects. Even though it is part of a terminal access server that can execute commands, this specific tool does not execute, modify, or delete anything—it merely reads the state of a session. The severity is low because an AI agent misusing this to read output poses minimal direct risk, though the broader server capabilities are concerning.
From the tool's definition The tool description states it 'Retrieve[s] latest output from a terminal session.' The verb 'retrieve' and the passive nature of reading output—as opposed to executing commands or modifying state—clearly indicates this is a Read operation.
Attacks that exploit this kind of access
Retrieve latest output from a terminal session. It is categorised as a Read tool in the TermPipe MCP MCP Server, which means it retrieves data without modifying state.
Register the TermPipe MCP server in PolicyLayer and add a rule for termf_live_output: 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 TermPipe MCP. Nothing to install.
termf_live_output 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 termf_live_output 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 termf_live_output. 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.
termf_live_output is provided by the TermPipe MCP server (wbind-core/termpipe-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 →