Skip to content

agentward-ai/agentward

Secrets & Credentials

Permission control plane for AI agents. MCP proxy that enforces least-privilege YAML policies on every tool call, classifies sensitive data (PII/PHI), detects dangerous skill chains, and generates compliance audit trails. Supports stdio and HTTP proxy modes.

Track releases GitHub
Python Latest v0.5.2 · 3mo ago Security brief →

Features

  • Scans AI agent tool definitions to identify risks
  • Enforces runtime policy in code outside the LLM context
  • Generates audit trails for compliance monitoring

Recent releases

View all 5 releases →
Review required
v0.5.2 New feature
Auth RBAC

EU AI Act + DORA + MiFID II audit framework

Open
Config change
v0.5.1 Breaking risk
Auth RBAC

HMAC audit + TTY approval + principal identity

Open
Config change
v0.5.0 Breaking risk

License change

Open
Review required
v0.3.2 New feature
Auth RBAC

HIPAA compliance eval & fix

Open

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
19
Forks
5
Languages
Python JavaScript Shell
View on GitHub

Install & Platforms

Install via
pip

Similar tools

getaegis/aegis
Ju571nK/sigil](https:
rsdouglas/janee
ArmorerLabs/Armorer-Guard
forest6511/secretctl

Beta — feedback welcome: [email protected]