Register an MCP server with NitroWatch so it can be watched

Connect to a registered server's real MCP endpoint and list its tools/resources/prompts

Project time-to-exhaustion on the team's 5M AI token budget

Generate a stub connector function that calls a tool on one registered server and pipes its result into a tool on another

Assign a risk tier (read / reversible / irreversible) to every tool on a registered server. Run this after discover_capabilities. Tries the LLM classifier first and falls back to the deterministic one.

Manually override a tool's risk tier when the classifier gets it wrong. Recorded as a human decision in the audit trail.

Ask NitroWatch to run a tool on a governed server. Read tools and promoted tools run immediately; everything else is queued for human approval and returns an approvalId.

Show every action currently blocked and waiting on a human decision, newest first. Renders the interactive approval console.

Human approves a pending action. Executes it, records the approval, and reports whether the tool has now earned promotion.

Human denies a pending action. Nothing executes, and the denial is recorded permanently against that tool.

Grant a reversible tool standing permission to run unattended. Requires a clean approval record. Irreversible tools are refused.

Withdraw a tool's autonomy immediately. It returns to requiring approval on every call.

Show the approval record and autonomy state for every governed tool — the evidence behind each promotion decision.

Return the full decision history: what was classified, allowed, blocked, approved, denied, promoted, and by whom.