Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
The Trend Vision One Model Context Protocol (MCP) Server enables natural language interaction between your favourite AI tooling and the Trend Vision One web APIs.
This project demonstrates how to build a multi-agent system using Agent-to-Agent (A2A) communication with the Model Context Protocol (MCP).
is a powerful tool that automatically detects APIs in existing projects and transforms them into Model Context Protocol (MCP) servers.
A centralized gateway for managing and connecting to multiple MCP (Model Context Protocol) servers. Provides secure, scalable access to MCP servers with SSO authentication, session isolation, and...
MCP-сервер для быстрого поиска по синтаксису 1С, предоставляющий ИИ-агентам в VS Code доступ к общей документации платформы 1С:Предприятие через централизованный сервис.
This is a simple example of how to use the Model Context Protocol (MCP) with OpenAI's API to create a simple agent acting from a chat context.
This repo showcases how to build Model Context Protocol (MCP) servers using Azure Cosmos DB. Explore ready-to-run samples in multiple programming languages including TypeScript,GoLang and Java.
Turn any MCP stdio server into HTTP endpoints your web app can call. Per-user session pooling, real timeout handling with background job fallback, live dashboard.
A Home Assistant Custom Component that provides an MCP (Model Context Protocol) server using , allowing AI assistants like Claude to interact with your Home Assistant instance.
[https://github.com/laurynas-biveinis/org-mcp/actions/workflows/elisp-test.yml] [https://github.com/laurynas-biveinis/org-mcp/actions/workflows/super-linter.yml] [https://melpa.
Conduct iterative, deep research using Google Gemini 2.5 Flash with Google Search Grounding and URL context. No web-scraping dependency is required.
让 AI 原生使用社媒数据的MCP服务。爬虫部分参考了MediaCrawler，将其 CLI 爬虫升级为 MCP 标准工具，让 Claude / ChatGPT 直连调用，一次配置，长期可用。
Agent Skills
Deep Discovery is a Codex plugin that adds the deep-discovery skill for a 100-question self-interrogation process before committing to a design, plan, or strategy.
跨平台的 draw.io (diagrams.net) 图表生成技能，适用于 Claude Code、codex、zcode、workbuddy、OpenClaw 等各类 AI 编程 Agent。Agent 直接生成 drawio XML，校验后通过 CLI 导出图片；没有桌面版时自动降级为 draw.io 官网打开链接。
yueban-image-to-code 是一个用于 Codex 的图片转代码与切图 skill，目标是把选中的 UI 图片或设计截图按 750px 画板宽度进行像素级还原，并导出独立透明 PNG 切图资源。
ling-mem is a single-binary CLI + optional web UI that remembers useful facts about you and your work across every session, every tool, and every project.
Three AI agents. $100K each. Real market prices. Who wins?
A comprehensive template repository system for bootstrapping AI-assisted development projects with Claude Code integration.
Generic skills used in my daily work
A skill that generates interactive HTML walkthroughs with clickable Mermaid diagrams — flowcharts and ER diagrams — to explain codebase features, flows, architecture, and database schemas.
面向 Python + pytest + requests 接口自动化项目的 AI Skill：让 Codex / Claude Code 按固定门禁、固定流程、固定 pytest 闭环来新增和维护接口自动化用例，流程图参考：flow_chart/flow.md。
VibeHub Skill 是一个面向普通人的 Vibe Coding 术语表达助手。它把不够准确的口语描述改成可以直接发给 Agent 的专业需求，也会主动指出当前场景里最值得认识的术语，附上通俗解释和 VibeHub 链接。
A small, shared skill library by builders, for builders.
One prompt. One .drawio file. Every icon renders correctly because the skill carries a verified catalog of 270+ stencil names, not guesses.