Search

PromptGuard MCP server — scan prompts, redact PII, and audit LLM SDK usage from any MCP client

https://github.com/Chill-AI-Space/vault-mcp

AI DevOps Automation Engine

Portable identity for AI agents across MCP, A2A, ANP, and AG-UI protocols

Create RevealUI projects with a single command

CrewAI tool for EnigmAgent — agents resolve {{PLACEHOLDER}} secrets at the call boundary so LLMs never see real API keys

Safety-first sandbox execution for agents, CI, and MCP tools — Python SDK and optional embedded runner.

Model Context Protocol (MCP) server for OpenClaw AI assistant integration

Shodan MCP server for Claude, Cursor & VS Code. 20 tools for passive reconnaissance, CVE/CPE intelligence, DNS analysis, and device search. 4 tools work free without an API key. OSINT and vulnerability research from your IDE.

MCP server exposing AgentMesh trust management tools for Claude, GPT, and other AI agents

MCP server for Lumu Defender API integration with Claude Desktop

The MCP bridge that audits your routes before exposing them to LLMs — and blocks prompt-injection at runtime.

MCP server for RugGuard — pre-trade rug-check API for AI agents. Wraps the x402 payment flow so Claude Desktop, Cursor, and other MCP-aware agents can call RugGuard without speaking x402 themselves.

Presentation layer — MCP server with stdio and HTTP transports.

CVE/vulnerability intelligence MCP server — 41 tools, 11 sources: NVD, EPSS, KEV, GHSA, OSV, Shodan, VulnCheck, Vulners, Nuclei, Metasploit, CIRCL, ATT&CK

SecretScan — Real-time secret & credential detector for Claude Code. 47 patterns covering Anthropic, AWS, GitHub, Stripe, database URLs, JWTs and more.

Access Japanese financial disclosures (EDINET). Search companies, retrieve BS/PL/CF statements.

A Wireshark MCP server for network packet analysis

Dark web intelligence MCP server — HIBP, ThreatFox, ransomware tracking, Tor .onion access, blockchain intel, exploit search, stealer logs, malware analysis

Behavioral litmus harness for MCP servers — grade a server A–F (tool-output injection, egress, sensitive-data, adversarial-input) with reproducible, content-addressed evidence. Ships a CLI and an MCP server with a run_litmus tool for AI agents.