// MCP TOOL REFERENCE

TERMINAL TOOLS

15 tools from the Terminal MCP Server, categorised by risk level.

// ALL 15 TERMINAL TOOLS

READ 3 tools

Read terminal_get_history Get past output from a terminal session. Read terminal_list List active terminal sessions. Read terminal_read Read new output from a terminal session.

WRITE 4 tools

Write terminal_resize Resize terminal dimensions. Write terminal_send_key Send a key to the terminal. Write terminal_write Write raw data to a terminal session. Write terminal_write_file Write content to a file.

EXECUTE 8 tools

Execute terminal_diff Run two commands and return a unified diff. Execute terminal_exec Execute a command in a terminal session and wait for it to finish. Execute terminal_retry Retry a command with backoff. Execute terminal_run Run a binary directly; avoid shell quoting. Execute terminal_run_paged Run a read-only command and return one page of output. Execute terminal_start Start a new interactive terminal session. Execute terminal_stop Stop and clean up a terminal session. Execute terminal_wait Wait for a pattern to appear in terminal output.

// FAQ

How many tools does the Terminal MCP server have? +

The Terminal MCP server exposes 15 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Terminal tools? +

Route the Terminal server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Terminal tools fall into? +

Terminal tools are categorised as Read (3), Write (4), Execute (8). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.