HKUDS/AnyTool
AnyTool is a Universal Tool-Use Layer that enhances AI agents by providing fast, scalable, and intelligent tool orchestration through smart context management and adaptive MCP tool selection.
Awesome MCP › Weekly › 2025-12-15
AnyTool is a Universal Tool-Use Layer that enhances AI agents by providing fast, scalable, and intelligent tool orchestration through smart context management and adaptive MCP tool selection.
Open Deep Wide Research is an open-source agentic RAG system with native MCP support that offers customizable control over sources, depth, and width for dynamic and cost-predictable research across various scenarios.
CUGA is an open-source configurable generalist agent designed for enterprise use, supporting complex web and API task execution with OpenAPI and MCP integrations, composable architecture, and advanced reasoning modes.
ARGO is an open-source local AI agent platform that integrates generative AI models and MCP tools to provide autonomous task planning, execution, and private offline operation for complex workflows.
Skillz is an MCP server that enables the loading, discovery, and execution of Claude-style skills for various AI agents, providing a flexible and standardized way to extend agent capabilities.
Playwriter is a browser extension-based Model Context Protocol (MCP) that enables efficient and powerful AI-driven browser automation using the full Playwright API with minimal context window usage.
Better Agents is a CLI tool and set of standards that enhance AI agent development by integrating Model Context Protocol (MCP) standards, ensuring best practices, testing, evaluation, and collaboration readiness.
Terminator is an open-source automation tool for Windows that leverages the Model Context Protocol to enable AI-driven desktop and browser automation with high reliability and speed.
PaperDebugger is an AI-powered academic writing assistant that integrates with Overleaf using a custom MCP-based orchestration engine to provide multi-step reasoning, reviewer-style critique, and structured revision for research papers.
Docfork MCP provides up-to-date documentation for over 9000 libraries directly within AI code editors using the Model Context Protocol, ensuring accurate and current code examples for developers and AI agents.
Grounded Docs MCP Server is an open-source, locally running MCP server that indexes and provides version-specific third-party documentation to AI coding assistants, improving accuracy and reducing hallucinations.
Strands Agents MCP Server is an MCP server that provides curated documentation access for Strands Agents to generative AI tools, enabling efficient search and retrieval of relevant information to facilitate AI agent development.
The Anytype MCP Server is a Model Context Protocol server that enables AI assistants to interact with Anytype's API through natural language, facilitating seamless knowledge base management.
An open-source project and course for building scalable, enterprise-grade AI automation systems using the Model Context Protocol, demonstrated through a Pull Request Reviewer integrated with GitHub, Slack, and Asana.
A comprehensive educational repository and course materials for understanding, implementing, and managing AI agents, with practical examples and integration of Model Context Protocol (MCP).
Open PTC Agent is an open source implementation of Programmatic Tool Calling (PTC) with MCP, enabling efficient and powerful code execution workflows for large language models in a secure sandbox environment.
mq is a jq-like command-line tool for processing and transforming Markdown files, with features supporting LLM workflows and an MCP server implementation for AI assistant integration.
JADX-MCP-SERVER is a Python-based MCP server that integrates with the JADX-AI-MCP plugin to enable live AI-assisted reverse engineering and vulnerability analysis of Android APKs using large language models like Claude.
Claude Task Master is an AI-powered task management system designed for AI-driven development that integrates seamlessly with various editors via the Model Control Protocol (MCP).
A comprehensive personal setup for Claude Code and OpenAI Codex featuring battle-tested skills, commands, hooks, agents, and MCP servers for enhanced daily productivity and automation.
An MCP server leveraging tree-sitter to provide intelligent, context-aware code analysis for AI assistants like Claude Desktop across multiple programming languages.
Osaurus is a native macOS LLM server with Model Context Protocol support, enabling local and cloud language model integration through a unified API, plugins, and developer tools optimized for Apple Silicon.
Strands Agents SDK for TypeScript is a model-driven, type-safe framework for building and running AI agents with native support for the Model Context Protocol (MCP) and multiple model providers.
DecoCMS is an open-source MCP-native Context Management System that centralizes and secures MCPs for AI workflows and agents, enabling full-stack TypeScript development, governance, observability, and flexible deployment across cloud and edge environments.