15 tools. 12 can modify or destroy data without limits.
12 write tools that can modify data. Rate limits recommended.
Last updated:
Write operations (terminal_resize, terminal_send_key, terminal_write) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (terminal_diff, terminal_exec, terminal_retry) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and Terminal. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @pungggi/smart-terminal terminal_resize:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
terminal_get_history:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
The Terminal server has 4 write tools including terminal_resize, terminal_send_key, terminal_write. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
15 tools across 3 categories: Execute, Read, Write. 3 are read-only. 12 can modify, create, or delete data.
One line change. Instead of running the Terminal server directly, prefix it with Intercept: intercept -c pungggi-smart-terminal.yaml -- npx -y @pungggi/smart-terminal. Download a pre-built policy from policylayer.com/policies/pungggi-smart-terminal and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init