Official Monte Carlo toolkit for AI coding agents. Skills and plugins that bring data and agent observability — monitoring, triaging, troubleshooting, health checks — into Claude Code, Cursor, and more.

Enable AI assistants to explore and query your Steampipe data!

Open-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.

Give AI agents safe access to your database.

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

A Model Context Protocol server that provides access to Shodan API functionality

AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schematics, review PCB layouts, EMC pre-compliance, SPICE simulation, download datasheets, source components, and prep boards for fabrication.

AI agent skills for building, operating and troubleshooting Apache Kafka applications. Topic audit, consumer lag, schema review, security, connectors and DLQ

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

Minimal Postgres editor for speed, collaboration, and AI

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

The Proxmox MCP you can hand the keys. All four products: PVE, PBS, PMG, PDM.

A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (DWS) Processor API, providing powerful PDF processing capabilities for AI assistants.

Redis' official collection of agent skills

MistTrack Agent Skills

An MCP server for querying Solana transactions using natural language with Solscan API

MCP server that connects AI assistants to HackerOne for bug bounty hunting

Connect any AI model to 1200+ integrations (MCP, CLI, API)

All-in-One malware analysis tool.

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.

🔌 A curated list of OSINT MCP servers. Pull requests are welcomed!

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.