Quick reference: Tools for evaluation
Index view. Tools are integrated into relevant week sections in
resources.md. This table tracks discovery dates for audit trail.
| Tool | Purpose |
|---|---|
eharris128/mcpsec |
MCP-focused security scanner |
snyk/agent-scan |
Snyk's agent-focused scanner |
agentic_security |
LLM vulnerability scanner + automated red teaming fuzzer [Apr-29] |
hexstrike-ai |
150+ pentesting tools via MCP for Claude/GPT/Copilot (8.3K stars) [Apr-29] |
guardrails-ai/guardrails |
Hard validation rules for agent ops before destructive actions (15K stars) [Apr-29] |
microsoft/agent-governance-toolkit |
Runtime policy enforcement, zero-trust identity, execution sandboxing; covers 10/10 OWASP ASI; 9,500+ tests [Apr-29] |
confident-ai/deepteam |
LLM red teaming framework; 50+ vulnerability probes covering OWASP/NIST/MITRE [Apr-29] |
splx-ai/agentic-radar |
CLI static scanner for agentic workflows; maps to OWASP LLM Top 10; runs locally [Apr-29] |
luckyPipewrench/pipelock |
AI agent firewall: MCP egress control, DLP, SSRF, prompt injection (342 stars) [Apr-29] |
affaan-m/agentshield |
Scanner for agent configs, MCP servers, tool permissions (CLI + GitHub Action, 567 stars) [Apr-29] |
FuzzingLabs/mcp-security-hub |
Offensive MCP tools wrapping Nmap, Nuclei, SQLMap, Ghidra, Hashcat (533 stars) [Apr-29] |
tldrsec/prompt-injection-defenses |
Comprehensive catalog of every known prompt injection defense (681 stars) [Apr-29] |