penholder
ai.penholder/penholder
Preventive human-approval write-gate for AI agents: writes commit only after a human approves.
Install surfaces
How penholder runs, per the official MCP registry entry.
- streamable-http
https://api.penholder.ai/mcp
Governed execution
How KLA gates calls to penholder once it is connected.
A published policy defines which penholder actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agents and model providers you already run. See integrations.