Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
A Model Context Protocol server built with Express.js that provides cryptographic tools including key pair generation, shared secret derivation, and message encryption/decryption.
The official GitHub Copilot plugins collection ✨
A comprehensive collection of examples demonstrating how to build AI agents that integrate with the Xero API using various agentic frameworks and the Xero MCP (Model Context Protocol) Server.
![GitHub Release][releases] ![GitHub Activity][commits]  ![HACS][hacs] ![BuyMeCoffee][buymecoffee]
Python boilerplate for creating AI agents, MCP servers, API microservices and monolith services. All in one!
MCP is a command-line tool and local UI for discovering, installing and managing Model Context Protocol servers.
Autonomous multi-agent AI system with document processing, web automation, and code execution powered by LLM agents and MCP servers
We have established this repository to serve as a comprehensive directory for resources related to the MCP, including items such as prompts, servers, and innovative ideas, all specifically tailored...
The Extension is open-source and at https://github.com/jasonkneen/mcpz-vscode and in the mcspx-tweaks branch
A custom MCP server that performs code reviews using Repomix and LLMs.
The open-source ecosystem for building, discovering, and deploying Model Context Protocol servers and clients for enterprise environments.
Agent Skills
MiniQMT 量化交易开发技能（miniqmt-skill）是一个基于迅投 XtQuant 库的量化交易开发工具，提供行情数据获取和交易执行功能。适用于开发股票、期货、期权等量化交易策略，支持历史/实时行情数据下载、K线/分笔数据获取、财务数据查询、自动下单/撤单、持仓查询、资产查询等功能。
Skills, agents, and templates for spec-driven development with Claude Code. Stack-agnostic at the core, with optional preset configs for common stacks (iOS+Firebase+Cloud Run, etc.).
微信聊天记录skill
Nix packaging for OpenClaw-adjacent tools, with per-tool OpenClaw plugin metadata. Part of the nix-openclaw ecosystem.
Design evaluation rubrics for LLM/agent outputs: criteria, scores, failure modes, examples.
On March 31, 2026, a .map file in Claude Code's npm package accidentally exposed the full TypeScript source. We read all 512,000 lines. Here's everything we found.
drpyS的技能仓库
这是一个专为 AI Agent（如基于大语言模型的编程助手）设计的 STM32 调试技能包（Skill）。它封装了常用的 STM32 固件编译、烧录、调试、寄存器查看以及变量实时监控功能，旨在让 AI 助手能够无缝、高效地协助开发者进行 STM32 嵌入式开发。
React components and CSS styles for Cozy apps
是 Anthropic 推出的模块化能力扩展机制，让 LLM 能够按需加载专业领域知识与工作流。本仓库收录了 开发的 Agent Skills 集合，实现 Claude 与其他 AI 模型、工具的无缝协作。
Write lightweight Architecture Decision Records for small teams: context → decision → consequences → status.
A set of skills to steer your AI-assisted machine learning experiments. The skills help you: