Block prompt injection before your AI agent reads it.
Sunglasses is a fast, local input filter for AI agents. It catches poisoned prompts, MCP/tool metadata and malicious agent instructions before they reach the model or your CI workflow.
0 cloud calls
Your agent trusts what it reads
Agents are attacked through what they read, not their code. Every attack class below is defined in plain words.
Full reference: Encyclopedia · 1583 patterns · MCP Attack Atlas
One boundary. 3 stages. 3.8ms median per attack string.
Content you route through Sunglasses passes through the same filter before any of it becomes model context.
Python API
One import, one call, one verdict object. Integrates with LangChain, CrewAI and Claude Code MCP workflows or your own loop.
Runs in CI
Insert it in your pipeline · scan repos, PRs and vendored tool metadata before they reach an agent.
MCP aware
Scans MCP tool metadata and docstrings · the surfaces the Attack Atlas documents · and pins each descriptor's hash so later changes are caught. With the local proxy (beta) server responses are inspected; without the proxy nothing is inspected automatically.
We publish what we don't catch, too
Patterns cite a live external reference or an internal fixture corpus, never uncited effectiveness numbers. When something is a hypothesis, we label it. No benchmark theater.
Real numbers, honest limits
97.4% recall on the shipped benchmark, 37/38 attacks, stated as exactly that, not a universal claim. 0 false positives on our clean-code corpus, 6 of 77 real-world READMEs flagged, including our own. The clean-corpus test runs in CI on every release.
Same problem. Different layer.
Other guardrail products are real tools doing real work. We are not here to replace them. Sunglasses is a free, local layer at the ingestion boundary: it catches known attack shapes before content reaches the agent, with no network call. Stack it under whatever else you run.
| Capability | Sunglasses |
|---|---|
| Text scanning | Yes |
| Image scanning | Yes (OCR + EXIF) |
| Audio scanning | Yes (Whisper) |
| Video scanning | Yes (subs + audio) |
| QR codes | Yes |
| Local execution | Always local |
| Works offline / air gapped | Yes, no cloud by default |
| No LLM required | Pattern based |
| Cost | Free (MIT) |
PDF: page text, metadata and annotations. Treat PDF results as partial for embedded or visual content.
We built Sunglasses to work with cloud security, not against it.
Already running cloud guardrails? Sunglasses is the local first pass that sits in front of them so nothing reaches your model or a paid API without being checked first.
Everything, defined and tested.
Open research on every attack class, mapped to the exact detection rules the scanner runs. All public.
Frequently asked questions
Put sunglasses on your agent
One pip install between your agent and everything it reads. Free, local and honest about what it catches.