Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
Production-grade MCP server for MikroTik RouterOS with secure AI-native network automation.
A Model Context Protocol (MCP) server that provides comprehensive access to MLB statistics and baseball data through a FastMCP-based interface.
Official remote MCP server for Trello.
MCP server for analyzing & generating docs for React code locally
🚀 MCP aggregator for batching multiple tool calls into a single request. Reduces overhead, saves tokens, and simplifies complex operations in AI agent workflows.
An MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.
Connect Claude and ChatGPT to KDAN PDF — upload, edit, compress, protect, redact, and compare PDFs in chat.
An MCP (Model Context Protocol) server that enables comprehensive research capabilities for Claude
Atari Lynx emulator, debugger, and embedded MCP server for macOS, Windows, Linux, BSD and RetroArch.
A guide on how to use the Amplitude MCP server
A model context protocol (MCP) server for Autodesk Fusion that provides resources and tools from ADSK to an AI client such as Claude or Cursor.
HA-MCP Custom Component - HACS distribution mirror of homeassistant-ai/ha-mcp (integration only)
Agent Skills
SigNoz Website
Open-source Claude Code plugin porting the internal /skillify skill: turn a finished session's repeatable workflow into a reusable SKILL.md you can rerun with a slash command.
Claude Code skill + Remotion scaffold for building polished product launch videos.
Permissionless infrastructure for agents. No human intervention required.
Develop Swift/iOS projects using VSCode
Sync and store bookmarks locally, manage Field Theory Library and command workflows, and make local context available to Claude Code, Codex, or any agent with shell access.
如果在使用过程中遇到问题，请通过 Issues 反馈功能正确性问题和功能请求，其他问题请通过 Discussions 反馈～
VS Code in the terminal
Generate app icon artwork and Google Play feature graphics from the terminal with OpenAI or Google Gemini.
Fill-in-your-own-data framework for YouTube / short-form video automation: CapCut JSON + ffmpeg tooling + an onboarding questionnaire. Ships with zero private data.
🚧 We are actively refining our core, resumption protocols, and runtime specifications, which will introduce major breaking changes prior to a stable release.
One Python API: store media, run models, index embeddings, serve endpoints, and version everything in a single system instead of gluing together blob storage, a vector DB, an orchestrator, and edge...