Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
AIShield Security Scanner
MCP serversScans MCP servers for tool poisoning, prompt injection and supply chain risks.
aishield-mcp-server@4.3.0 -
unicode-security-mcp
MCP serversLocal checks for Unicode confusables, mixed scripts, invisible controls, and suspicious identifiers.
unicode-security-mcp@1.0.1 -
Seal Security
MCP serversVulnerability management: scan projects, search sealed packages, manage sealing rules and reports.
-
gmi-security-mcp
MCP serversTriage semgrep findings with GMI Inference, with cost shown before every run.
gmi-security-mcp@0.5.11 -
godot-mcp-enhanced
MCP serversEnhanced Godot 4.5-4.7 MCP: headless+editor+bridge, secure GDScript sandbox, closed-loop AI dev.
godot-mcp-enhanced@0.24.0 -
spring-ai-privacy-guardrails
MCP serversPrivacy guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and optional Spring Security tool authorization. Supports Presidio and JVM-local OpenNLP.
git clone https://github.com/ultramancode/spring-ai-privacy-guardrails.git -
UNVERIFIED: cross-cloud beta; sandbox by default; production opt-in via customer Guardian.
@securestamp/execution-guardian-mcp@0.3.0-beta.2 -
cybersec-toolkit
MCP serversMCP server that catalogs 670+ security tools and runs installed ones under a scope and audit policy.
ghcr.io/26zl/cybersec-toolkit:1.5.0 -
agentlint
Agents & frameworksLocal guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more
git clone https://github.com/mauhpr/agentlint.git -
stigix
MCP serversStigix is a lab platform to validate SD‑WAN and SASE. It unifies SaaS traffic generation, security tests, convergence probes, and voice/IoT/VyOS simulations in one web UI
git clone https://github.com/jsuzanne/stigix.git -
Ubuntu security: USNs per CVE, patched versions. Be born in one call — free testnet funds.
-
FHI MCP Server Security Audit
MCP serversFree payment guide and Base-USDC x402 MCP security, package, domain, and SEC tools.
-
Singularity - MCP Discovery & Security Gateway
MCP serversFind, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
-
PYRESEC - AI Code Security Auditing
MCP serversAI code security audits via x402 USDC: $0.01 scans, $0.50 audits, $5 auto-fixes. SAST/SCA.
-
EdgeScreen x402 Security Screening
MCP serversFree MCP hooks + x402 security scans; MCP manifest and SKILL.md audits cost $0.003 Base USDC.
-
langkit
Prompts🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
git clone https://github.com/whylabs/langkit.git -
xorcise
Datasets & benchmarksRun cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.
git clone https://github.com/xorcise-ai/xorcise.git -
Bug Bounty Programs - HackerOne + Bugcrowd Lookup | Bulk
-
Agent Security Scanner
MCP serversScan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
agentvuln@0.4.2 -
Secure Schema MCP
MCP serversRead-only MCP server for exposing database schema metadata without row data.
mcp-secure-schema@1.0.1 -
security-preflight
MCP serversStatic MCP, source-code and injection-indicator checks with redacted signed receipts.
-
RelayShield Security Intelligence
MCP serversBreach, SIM swap, infostealer, domain lookalikes, MCP registry risk, prompt-injection detection.
relayshield-mcp@0.3.0 -
SecurityScan
MCP serversScan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
-
--- name: comprehensive-web-application-development-with-security-and-performance-optimization description: Guide to building a full-stack web application with secure user authentication, high performance, and robust…
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.