AI agents call get_terminal_output to retrieve information from VibeWatch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves historical terminal output for monitoring purposes. While terminal output may contain sensitive information (credentials, API keys, file paths), the tool itself performs no side effects, no code execution, and no data modification. It's a passive log viewer.
From the tool's definition Tool name 'get_terminal_output' and description 'Get the last N lines of terminal output from a monitored development process' indicate this retrieves/queries existing data (terminal logs) without modifying or executing anything.
Attacks that exploit this kind of access
Get the last N lines of terminal output from a monitored development process. Use this to see what\. It is categorised as a Read tool in the VibeWatch MCP Server, which means it retrieves data without modifying state.
Register the VibeWatch MCP server in PolicyLayer and add a rule for get_terminal_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 VibeWatch. Nothing to install.
get_terminal_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 get_terminal_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 get_terminal_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.
get_terminal_output is provided by the VibeWatch MCP server (krjordan/vibewatch). 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 →