guardana MCP Server
guardana/guardana
[](https://agentrank-ai.com/tool/guardana--guardana/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
guardana/guardana is a Python MCP server licensed under Apache-2.0. Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions. Topics: ai-red-teaming, ai-safety, ai-security, llm-security, ml-security, mlsecops, model-security, owasp-llm, prompt-injection, python, sarif, security-tools, supply-chain-security, agent-security, ai-agents, devsecops, mcp, model-context-protocol, opentelemetry, red-teaming.
Ranked #6899 out of 24846 indexed tools.
Ecosystem
Score Breakdown
272 stars → growing community
Last commit 29d ago → recently updated
0/18 issues closed → many open issues
2 contributors → solo project
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Matched Queries
From the README
<div align="center"> # 🛡️ Guardana Guardana is an open-source AI security verification tool for security and platform engineers. It checks code and model artifacts, live AI systems, and recorded runs. It reports what it found, what it could not verify, and what it could not check. It verifies outside the request path; it is not an inline guardrail, a general SAST or CVE scanner, or a compliance certification. [Quickstart](#quickstart) · [Features](FEATURES.md) · [Rule catalog](docs/generated/rule-catalog.md) · [Docs](docs/index.md) · [Status & limits](docs/product-status.md) · [Current work](https://github.com/guardana/guardana/issues) · [Changelog](CHANGELOG.md) · [Get involved](#get-involved) </div> --- **58 built-in security checks; add checks for your application.** The count comes from the [generated rule summary](docs/generated/rule-summary.md). Built-in artifact checks need no network. `scan --reporter server://<url>` sends results to a collector; active checks contact thRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.