Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MCP MySQL Server 是一个基于 @modelcontextprotocol/sdk 的 MySQL 工具服务，支持 SQL 查询、表结构获取、连接检测等功能，适用于 AI 代理、自动化工具等场景。
MCP server for Fly.io CLI integration with Claude Desktop
I've been running this Gemini MCP server in my Claude Desktop setup for months. It's one of the few I leave on permanently — not because Gemini replaces Claude, but because grounded search, image...
The jMRI (jMunch Retrieval Interface) specification — an open interface standard for token-efficient context retrieval in MCP servers.
is a media-generation agent: generate images, video, and audio, transcribe, render HTML, search the web, run code, and chain multi-step media operations — from any MCP client.
Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff & frontend↔backend integration.
Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Claude & any MCP client persistent cross-session memory.
让你的 AI 大模型成为企业微信开发专家 - 1 MCP · 41 Skills · 550+ APIs · 三大开发模式全覆盖 —— Make Your AI Model a WeCom Development Expert - 1 MCP · 41 Skills · 550+ APIs · Comprehensive Coverage of Three Major Development...
Local MCP bridge for image understanding and web-page reading with OpenAI-compatible models
Traditional eSignature tools lock you into rigid, static PDF files. takes a different approach — contracts remain throughout their entire lifecycle, making them effortless for developers, automation...
MCP Server for the National Park Service (NPS) API, providing real-time information about U.S. National Parks, including park details, alerts, and activities.
Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON
Agent Skills
Econ Writing Skill is an open-source Agent Skill that gives AI coding assistants deep knowledge of how to write economics papers.
photo-revival 是一个 Codex Skill。它不是给照片套滤镜，而是把照片当成“记忆证据”：保留主体、空间关系和情绪，再用新的手绘插画语言重新生成。
A production-ready OpenClaw plugin that implements the A2A (Agent-to-Agent) v0.3.0 protocol, enabling OpenClaw agents to discover and communicate with each other across servers — with zero-config...
An open-source Dynamic Workflow runtime for building observable, reusable Agent graphs.
Use the coding agents, browser sessions, desktop apps, notifications, and tool access you already have.
Swift Testing Agent Skill for AI Coding Assistants
Drag-and-drop email editor for modern apps — source-available, MIT after two years
新论文层出不穷，英文读得再顺也不如母语省心；我们想把这些论文变成排版规范、读着顺口的中文 PDF。
一个适用于 Claude Code / Codex 的技能，用来生成惊艳、带动画、单文件的 HTML 演示文稿，并内置浏览器编辑器：可拖拽对象、调整大小、编辑文本、重排页面、本地保存，并导出干净的独立 HTML。
This is the template to be used together with the Digital Garden Obsidian Plugin. See the README in the plugin repo for information on how to set it up.
SkVM is a compilation and runtime system that makes LLM agent skills portable across heterogeneous models and harnesses. It has four major parts:
A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access.