AgentSkillsHub
Search, audit, and install from 117K+ open-source AI agent skills & MCP servers — every result carries a security grade (SAFE/CAUTION/UNSAFE/UNAUDITED) and…
Directory
Search MCP Servers
Desktop Commander
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
ToolHive
A lightweight utility designed to simplify the deployment and management of MCP servers, ensuring ease of use, consistency, and security through…
Cloudsword
CloudSword is an open-source tool designed to help public cloud tenants quickly discover, test, and improve security in their cloud environments. Targeted at…
CLI
An MCP server to run arbitrary commands on the local machine.
Identity
AGNTCY Identity allows to onboard, create and verify identities for Agents, Model Context Protocol (MCP) Servers and Multi-Agent Systems (MASs).
OpenAPI
Integrates with OpenAPI specifications to expose REST API endpoints as MCP resources, enabling dynamic discovery and utilization of many web services.
PiAPI
PiAPI MCP server makes user able to generate media content with Midjourney/Flux/Kling/Hunyuan/Udio/Trellis directly from Claude or any other MCP-compatible…
Minibridge
A backend-to-frontend bridge that securely exposes MCP servers to the internet, supporting agent authentication, content analysis, transformation, and…
Google Keep
Provides a bridge to Google Keep for searching, creating, updating, and deleting notes with safety features that restrict modifications to specifically labeled…
MCP Notes
Integrates note-taking capabilities with AI models using TypeScript and DynamoDB for persistent memory and context management in applications.
Dify
Integrates Dify AI API to provide code generation for Ant Design components, supporting both text and image inputs with stream processing capabilities.
Speclock
AI constraint engine — persistent memory + active enforcement. Stops AI from breaking locked code. Semantic conflict detection, file-level guards, session…
Filesystem (Rust)
Provides secure filesystem operations within allowed directories for controlled file management and data processing tasks.
GUARDRAIL: Security Framework for Large Language Model Applications
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
SchemaPin 🧷
The SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
CyberMCP - Cybersecurity API Testing with MCP
CyberMCP is a Model Context Protocol (MCP) server designed for testing backend APIs for security vulnerabilities. It provides a set of specialized tools and…
AWS SSO MCP Server
Node.js/TypeScript MCP server for AWS Single Sign-On (SSO). Enables AI systems (LLMs) with tools to initiate SSO login (device auth flow), list accounts/roles…
Binalyze AIR MCP Server
Interact with Binalyze AIR's digital forensics and incident response capabilities using natural language.
Dumpling AI MCP Server
Provides a bridge to Dumpling AI's data extraction API for performing web searches, scraping content, extracting structured data, and processing various…
Obsidian
Integrates with Obsidian vaults, enabling natural language queries and updates to notes through secure read/write access.
Schwab
The Schwab Model Context Protocol (MCP) Server connects your Schwab account to LLM-based applications (like Claude Desktop or other MCP clients), allowing them…
Harvest Time Tracking
Integrates with Harvest time tracking API for creating, updating, and managing time entries, clients, projects, and reports within your workflow.
MCP_TOOL_POISONING_ATTACKS
A Node.js project demonstrating MCP client and server interactions for tool poisoning attacks, requiring an Anthropic API key.