terminal_history

Get command history for a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.

Server Claude Flow claude-flow
Category Read
Risk class Low
Parameters 00 required

What terminal_history does on Claude Flow

AI agents call terminal_history to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why terminal_history needs a policy

This tool retrieves historical command records from a terminal session—a read-only query operation. While terminal history can reveal sensitive information (commands, arguments, credentials in logs), the tool itself performs no destructive, write, or execute actions. The severity is low because misuse amounts to information disclosure rather than code execution or data destruction.

From the tool's definition Tool name 'terminal_history' and description phrase 'Get command history' indicate retrieval of past terminal session data with no mention of command execution, modification, or deletion.

Questions about terminal_history

What does the terminal_history tool do? +

Get command history for a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on terminal_history? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for terminal_history: 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 Claude Flow. Nothing to install.

What risk level is terminal_history? +

terminal_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit terminal_history? +

Yes. Add a rate_limit block to the terminal_history 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.

How do I block terminal_history completely? +

Set action: deny in the PolicyLayer policy for terminal_history. 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.

What MCP server provides terminal_history? +

terminal_history is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.