Assay

Policy-as-Code for AI Agents

Assay is a Policy-as-Code engine for the Model Context Protocol (MCP). End-to-end governance pipeline: trace capture → policy generation → deterministic CI replay gating → verifiable evidence bundles → signed compliance packs.

Install¶

curl -fsSL https://getassay.dev/install.sh | sh

Core Capabilities¶

Policy Enforcement

Validate tool calls against JSON Schema constraints, sequence rules, and allowlists. No LLM calls in CI.

Policy Reference
Evidence Bundles

Tamper-evident audit trails with content-addressed IDs. CloudEvents v1.0 format. SARIF output for GitHub Security. Combine with BYOS append-only storage for audit-grade completeness.

Evidence Guide
Compliance Packs

Built-in rule packs that structure engineering evidence for EU AI Act, SOC 2, and custom policies. Article-referenced findings for auditors. Packs do not constitute legal compliance on their own.

Pack Engine
Tool Signing

Ed25519 signatures for tool definitions. DSSE envelope format. Trust policies for supply chain security.

Signing Spec

Quick Start¶

1. Capture Traces¶

assay import --format inspector session.json --out-trace trace.jsonl

2. Validate¶

assay validate --trace-file trace.jsonl --format sarif

3. Export Evidence¶

assay profile init --output assay-profile.yaml --name quickstart
assay evidence export --profile assay-profile.yaml --out bundle.tar.gz
assay evidence verify bundle.tar.gz

4. Lint with Compliance Pack¶

assay evidence lint --pack eu-ai-act-baseline bundle.tar.gz

Result	Exit Code	Output
Pass	`0`	Summary
Fail	`1`	SARIF with findings
Error	`2`	Config/Schema validation

GitHub Action¶

- uses: Rul1an/assay-action@v2

Zero-config. Discovers evidence bundles, verifies integrity, uploads SARIF to GitHub Security.

GitHub Action Guide

Defense in Depth: Runtime Enforcement (Linux, Optional)¶

Optional kernel-level hardening for Linux deployments.

# Landlock sandbox (rootless)
assay sandbox --policy policy.yaml -- python agent.py

# eBPF/LSM kernel-level enforcement
sudo assay monitor --policy policy.yaml --pid <agent-pid>

Standards Alignment¶

Standard	Integration
CloudEvents v1.0	Evidence envelope format
W3C Trace Context	`traceparent` correlation
SARIF 2.1.0	GitHub Code Scanning
EU AI Act Article 12	Compliance pack mapping