Search
model-secure
proofxhq
Cryptographic signing and verification for AI model files. Prove your model hasn't been tampered with.
tokendna-sdk
TokenDNA
Identity for AI agents in one decorator. Native LangChain, CrewAI, AutoGen, and MCP middleware with attestation, delegation, and behavioral baselines.
...moregraphql-query-depth-limit-esm
GitHub Actions
GraphQL query depth limiting validation rule with directive support, ignore rules, and fragment cycle detection
@cchsh/skill-shield
cchsh
Static and semantic-risk scanner for Agent Skills.
auditx
parth308
One command. Every vulnerability, dead code, and AI-generated code anti-pattern. JSON output built for AI coding agents to parse and self-fix.
...more@agent-mcp-tools/mcp-slim-guard
lennney
MCP proxy for schema compression, tool access control, SSRF protection, injection detection, rate limiting and audit logging
...more@gendigital/sage-mcp
vaclavbelak
Safety for Agents — shared MCP server for Sage connectors
aiignore-cli
yjcho9317
One command to protect your secrets from all AI coding tools
aws-vpc-analyzer
Ayush Goel
MCP server for AWS VPC network topology analysis using NetworkX directed graphs
eol-check
abhishekpanda06202
CLI tool to check End-of-Life (EOL) status of code, infrastructure, containers, and AI models. Supports Docker, Terraform, AWS, Serverless, and more.
...moreneutralai-sdk
NeutralAI
Official NeutralAI Python SDK for masking sensitive prompt data before it reaches AI applications.
io.github.Sentinel-Gate/sentinelgate
Sentinel-Gate
Open-source MCP proxy for AI agent access control with CEL policies, RBAC, and audit.
embeddings-guardian
Open-source RAG poisoning detection. OWASP LLM08:2025 reference implementation.
airlock-agent
Airlock
Runtime firewall for AI coding agents — gate every tool call, MCP call and skill against a least-privilege policy.
safe-buffer
feross
Safer Node.js Buffer API
mcp-output-firewall
Jet
Three-layer firewall for MCP servers — content inspection, egress policy and action policy. Catches prompt injection, tool poisoning, exfiltration and leaked secrets before they reach your agent.
...more@nodatachat/protect
nodatachat
Encrypt .env secrets with AES-256-GCM. Decrypt in memory only. Cryptographic proof of every access. Claude Code Skill included.
...moreredactum
alexwhin
Comprehensive PII redaction library for AI applications with framework adapters for LangChain, LlamaIndex, Haystack, OpenAI SDK, Anthropic SDK, and Vercel AI SDK
...more@miaggy/mcp-audit
auaggy
Audits the MCP servers configured on a machine for supply-chain risk: unpinned versions, inline secrets, missing provenance, install scripts, maintenance signals
...moremcp-tool-auditor
Përparim Mjeku
MCP Tool Poisoning Scanner — Defensive scanning + offensive pentest tooling for MCP servers. Maps to OWASP MCP Top 10.