Returns recent terminal output (ANSI-stripped). Use this to read what
AI agents call terminal-read to retrieve information from Mcp Terminal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reads data from terminal sessions without modifying or executing anything. It is fundamentally a Read operation. Severity is medium rather than low because terminal output can expose sensitive information depending on what commands were previously executed in that session.
From the tool's definition Tool name 'terminal-read' and description 'Returns recent terminal output' indicate data retrieval without modification.
Attacks that exploit this kind of access
Returns recent terminal output (ANSI-stripped). Use this to read what. It is categorised as a Read tool in the Mcp Terminal MCP Server, which means it retrieves data without modifying state.
Register the Mcp Terminal MCP server in PolicyLayer and add a rule for terminal-read: 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 Mcp Terminal. Nothing to install.
terminal-read 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 terminal-read 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 terminal-read. 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.
terminal-read is provided by the Mcp Terminal MCP server (unfathomable-siren38/mcp-terminal-server). 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 →