Agentic Security Shield
io.github.ormuzdo/agentic-security-shield
12-layer security configs for AI coding agents. Autonomous purchase via x402 (USDC on Base).
Install surfaces
How Agentic Security Shield runs, per the official MCP registry entry.
- streamable-http
https://agentic-security-shield-mcp-production.up.railway.app/mcp
Governed execution
How KLA gates calls to Agentic Security Shield once it is connected.
A published policy defines which Agentic Security Shield 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 agent frameworks and model providers you already run. See integrations.