Documentation

Shrike Documentation

Everything you need to govern what your AI agents do — every tool call, command, and query evaluated against your policy before it runs. It catches prompt injection, data leakage, and unsafe actions along the way.

Quick StartStart Here

Get scanning in 5 minutes. Sign up, grab an API key, and run your first security scan.

Agent FrameworksFor builders

Compose Shrike into a LangGraph, LangChain, or CrewAI agent as four layers — an enforcement floor the model can't skip, plus the agency it consults through. Governance the agent listens to, not a filter bolted on.

SDK Reference

Python and TypeScript SDKs. Integrate AI security in 3 lines of code.

API Reference

REST endpoint documentation for the Agent and Dashboard services.

MCP Server

Protect Claude Desktop, Cursor, and Windsurf with 14 security tools.

Agent Scope DeclarationNew

Declare what an agent is for — purpose, allowed tools, expiry. Out-of-scope calls route to human approval before they execute. You declare; Shrike enforces.

Cookbook — Working with ShrikeNew

Drop-in system-prompt block that teaches your agent how to react to Shrike verdicts. ~180 words. Copy, paste, ship.

OWASP Agentic Top 10 → ShrikeNew

Every risk in the OWASP Top 10 for Agentic Applications (2026) — ASI01 Agent Goal Hijack through ASI10 Rogue Agents — mapped to where Shrike enforces at the action layer.

Compliance

NIST AI RMF, SOC 2, HIPAA, and ISO 27001 alignment documentation.

Need help? Contact support or visit our GitHub.