Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
mcpsec
MCP serversAn AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.
git clone https://github.com/manthanghasadiya/mcpsec.git -
Intelligent Vulnerability Triage Analyze GHAS alerts across repositories Identify dependency vs base image root causes Detect repeated vulnerability patterns Prioritize remediation based on severity and exposure Safe…
-
arkon
MCP serversArkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.
git clone https://github.com/nduckmink/arkon.git -
AgentPoison
Agents & frameworks[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
git clone https://github.com/AI-secure/AgentPoison.git -
theauth
MCP serversAuth for AI agents and humans. First-class agent identity, MCP OAuth 2.1, delegation, audit. TypeScript, edge-native, MIT.
git clone https://github.com/glincker/theauth.git -
atlassian-mcp-server
Tools & appsOfficial remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
git clone https://github.com/atlassian/atlassian-mcp-server.git -
ServerFS_MCP
SkillsSecure, scoped filesystem MCP server for ChatGPT and other MCP clients — read-only by default, with controlled mutations, binary transfer, native Codex/Claude/Qoder runtimes, generic ACP v1 profiles, and Agent Skills.
git clone https://github.com/NTLx/ServerFS_MCP.git -
disrobe
MCP serversStatic decompiler, deobfuscator, and unpacker for reverse engineering and malware analysis: Python decompiler (3.8-3.15), PyInstaller extractor, PyArmor unpacker, JavaScript deobfuscator (obfuscator.io, JS-Confuser, webpack), Android APK and Java decompiler, .NET deobfuscator, UPX unpacker, Lua, PHP, WASM, PowerShell. MCP server.
git clone https://github.com/1-3-7/disrobe.git -
HealthClawGuardrails
SkillsOpen-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
git clone https://github.com/aks129/HealthClawGuardrails.git -
sre
Agents & frameworksThe SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.
git clone https://github.com/SmythOS/sre.git -
LinkWork
Agents & frameworksOpen-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native scheduling
git clone https://github.com/momotech/LinkWork.git -
IPLogs
Public APIsFree VPN, proxy, Tor and datacenter IP detection. 13 sources, active probing
-
Cisco PSIRT openVuln API
Public APIsThe Cisco Product Security Incident Response Team (PSIRT) openVuln API is a RESTful API that allows customers to obtain Cisco Security Vulnerability information in different machine-consumable formats. APIs are important for customers because they allow their technical staff and programmers to build tools that help them do their job more effectively (in this case, to keep up with security…
-
mcp-bastion
MCP serversReliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.
mcp-bastion@1.5.0 -
pincer
MCP serversSecure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture
pincer-mcp@0.1.5 -
AegisGate MCP
MCP serversSecure MCP server framework with 23 security layers and ML threat detection. Zero deps.
ghcr.io/aegisgatesecurity/aegisgate-mcp:1.5.1 -
lighthouse-mcp-server
MCP serversMCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis.
git clone https://github.com/danielsogl/lighthouse-mcp-server.git -
squirrelscan
SkillsThe website QA tool for your coding agent. 310+ audit rules across SEO, performance, security, accessibility and agent experience.
git clone https://github.com/squirrelscan/squirrelscan.git -
Bello
Agents & frameworks3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in parallel, have them check each other’s work, and reduce unnecessary model calls and noisy tool output. Turn on only what you need.
git clone https://github.com/Makson179/Bello.git -
Maskbreak
Public APIsDetect VPNs, proxies, Tor, bots and antidetect browsers at signup, login and checkout
-
Spyse
Public APIsAccess data on all Internet assets and build powerful attack surface management applications
-
RealBots
Public APIsVerify whether requests claiming to be GPTBot, ClaudeBot & other AI crawlers are real
-
forge
Agents & frameworksForge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, air-gapped, embedded in CI, or as an A2A endpoint.
git clone https://github.com/initializ/forge.git -
terrashark
SkillsTerraform Skill for Claude Code and Codex. LLMs hallucinate a lot with Terraform - TerraShark fixes this. It eliminates hallucinations, is designed for modular and secure code and grounds your IaC in the official Hashicorp Terraform best practices.
git clone https://github.com/LukasNiessen/terrashark.git
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.