Safer agent skills

Let LLMs control embedded devices via the Model Context Protocol.

Score basis：Clear source · Risk needs review · Universal

Browser automation via Playwright MCP server.

Score basis：Source needs review · High risk signals · Claude

A Model Context Protocol (MCP) server for interacting with the MetaTrader 5 trading platform.

Score basis：Clear source · Risk needs review · Universal

A Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar.

Score basis：Clear source · Risk needs review · Universal

🟪 Open source Agent Governance Platform that turns any LangGraph or ADK agent into a production-ready service.

Score basis：Clear source · Risk needs review · Universal

Automate Xiaohongshu (RedNote) content operations using a Python client for the xiaohongshu-mcp server.

Score basis：Source needs review · High risk signals · Claude

A Model Context Protocol (MCP) server that enables AI assistants to securely access and analyze Microsoft Fabric Analytics data through authenticated API calls.

Score basis：Clear source · Risk needs review · Universal

🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search.

Score basis：Clear source · Risk needs review · Universal

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines Topics: deepseek, demo, easy, embedding, flask, gpt, huggingface-transformers, llm, mcp, multimodal, openai, qwen.

Score basis：Clear source · Low risk signals · Universal

VSCode Extension with an MCP server that exposes semantic tools like Find Usages and Rename to LLMs Topics: cline, cursor, cursor-ai, developer-tools, mcp, mcp-server, vscode, vscode-extension, windsurf.

Score basis：Clear source · Low risk signals · Universal

🔍 Enable AI assistants to search, access, and analyze PubMed articles through a simple MCP interface.

Score basis：Clear source · Risk needs review · Universal

A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation,compaitable with react,svelte 5,vue & React Native Topics: ai, expo, mcp, modelcontextprotocol, nextjs, npm, npm-package,

Score basis：Clear source · Low risk signals · Universal

MCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objective-C APIs & code examples in Claude, Cursor & AI assistants Topics: ai-assistant, api-documentation, apple, ap

Score basis：Clear source · Low risk signals · Universal

A battle of balls game, lol style, AI Agents base, support agent skills & unityMCP.

Score basis：Clear source · Low risk signals · Universal

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.

Score basis：Clear source · High risk signals · Claude

A Model Context Protocol (MCP) server that provides access to the Fastmail API, enabling AI assistants to interact with email, contacts, and calendar data.

Score basis：Clear source · Risk needs review · Universal

Intelligent Python system that extracts real estate property data as structured JSON using AI agents, Nebius Qwen LLM, and Bright Data MCP.

Score basis：Clear source · Risk needs review · Universal

Flexible GraphRAG: Python, LlamaIndex, Docker Compose: 8 Graph dbs, 10 Vector dbs, OpenSearch, Elasticsearch, Alfresco.

Score basis：Clear source · Low risk signals · Universal

Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps

Score basis：Clear source · Risk needs review · Universal

A Model Context Protocol (MCP) implementation for Splunk Enterprise and Cloud integration with Cursor IDE or Claude

Score basis：Clear source · Risk needs review · Universal

MCP server for Garmin Connect — access 61 health, fitness and activity tools from any AI assistant

Score basis：Clear source · Risk needs review · Universal

Letting Claude Code develop his own MCP tools :)

Score basis：Clear source · Risk needs review · Universal

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

Score basis：Clear source · Risk needs review · Universal

The Mind Palace for AI Agents — Autonomous Cognitive OS with affect-tagged memory (valence engine), token-economic RL (surprisal gate + UBI), Hebbian learning, ACT-R spreading activation, Synapse Engine (GraphRAG), adve…

Score basis：Clear source · Risk needs review · Universal