Assess Agent & MCP security Defense
Weir
Weir plants unique fake API keys into an AI agent's environment, runs the agent's flows against a local fake model, and checks every span, log, console output, model prompt and outbound request for those exact values. It also offers a Claude Code status line and redaction hook that track real keys entering or leaving sessions.
Promising or important to understand; evaluate, don't depend on it yet.
Facts
- Repository
- ralis-ai/weir
- Homepage
- github.com
- Listed via
- Curated
- First seen
- 2026-11-09
- License
- Apache-2.0
- Stars
- 19
- Last commit
- 2026-11-09
- Latest release
- v0.9.0 · 2026-11-08
- Checked
- 2026-11-10
Techniques
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.