Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
This bridge implements Anthropic's discovery pattern with rootless security—reducing MCP context from 30K to 200 tokens while proxying any stdio server.
A Model Context Protocol (MCP) server that integrates with OpenAI's Sora 2 API for video generation and remixing.
: The project structure has changed. If upgrading from v0.1.0, update your configuration: - Change uv run server.
Connect Claude Code and other AI tools to your Obsidian notes using Model Context Protocol (MCP)
A Model Context Protocol (MCP) server designed to facilitate software development planning through an interactive, structured approach.
A MCP Server for Google Scholar: 🔍 Enable AI assistants to search and access Google Scholar papers through a simple MCP interface.
: This is an , community-developed MCP server and is affiliated with or endorsed by Interactive Brokers. This software is in and may not work perfectly.
An Android application that runs as an , enabling AI models to remotely using accessibility services and screenshot capture.
Semantic Code Retrieval for AI Agents — Hybrid Search • Graph Expansion • Token-Aware Packing
A lightweight Model Context Protocol (MCP) server that provides through just 3 tools. Compatible with .
mcp-servers-for-revit enables AI clients like Claude, Cline, and other MCP-compatible tools to read, create, modify, and delete elements in Revit projects.
A Model Context Protocol (MCP) server for interacting with Ghost CMS through LLM interfaces like Claude.
Agent Skills
为电影改AI影视而生，面向 Agent 的电影级画面 Prompt Skill，专门生成 HBO / 好莱坞质感的生图提示词与 LOOK 迁移、一致性方案
Turn any app into a cinematic motion graphics promo video using AI.
OmniBox-Spider-Skills 是一个面向 OmniBox 爬虫开发的技能仓库，提供可复用的技能说明、规则约束与结构化参考文档，帮助开发者更快完成爬虫源的编写、调试、回归检查与持续维护。
Skill to generate the knowledge vault for projects using the Ralph loop
Anything2Ontology is a 4-module pipeline that ingests raw media (PDFs, slides, spreadsheets, YouTube videos, GitHub repos, websites), extracts structured knowledge, and assembles a self-contained...
A collection of AI assistant skills for vLLM-Omni -- a framework for efficient omni-modality model inference supporting text, image, video, and audio.
Codex Manager is a desktop configuration and asset manager for OpenAI Codex. It edits and organizes on-disk Codex files with a safety-first flow (diff preview, backups, atomic writes), surfaces local...
微信公众号自动化运营 OpenClaw Skill - 内容采集、数据分析、互动管理
🎨 Live Gallery · ⚡ Install · 💡 Why HTML? · ⭐ Browse 116 demos
Turn a messy browser bookmark export into a clean, searchable, local navigation site — plus structured data, Markdown overviews, and review reports.
Expert automation skills for Claude Code, organized by department.
AutoRename-PDF Automatically rename PDF files using AI and OCR. Extracts company names, dates, and document types from any PDF — renames to YYYYMMDD COMPANY DOCTYPE.pdf .