Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Universal Memory Protocol (UMP) - an open standard for agent memory. The third interop layer beside MCP (tools) and A2A (coordination).
Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM needed). MCP server for AI agents with 500x fewer tokens.
Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
Plug-and-play MCP that gives your coding agent UI superpowers. One-line install, zero config. Claude Code, Codex, Cursor, VS Code, and more.
Production-grade memory operating system for agentic AI. Interoperates with every major framework via MCP, OpenAI-compatible gateway, and native /v1/* REST — Claude Code, OpenClaw, ZeroClaw, Hermes,...
Production-ready MCP servers for 70+ APIs — GitHub, Google, Notion, Jira & more. Generated from OpenAPI specs, tested against live APIs. Works with Claude Desktop, Cursor, Codex & Claude Code.
MCP server for Web3 protocol documentation — EIPs, ERCs, BIPs, SIMDs, Cosmos ADRs, Polkadot RFCs, contract registry
An MCP server that runs AI-driven venture capitalist agents (Fred Wilson, Peter Thiel, etc.), whose thinking is continuously enriched by Octagon Private Markets' real-time deals, valuations, and deep...
The universal MCP server for Claude Code and other MCP-compatible clients. One installation gives AI access to 10,000+ PowerShell modules and any CLI tool.
Define TypeScript capabilities that send emails, manage calendars, and automate work. Expose them to the Routecraft agent, Claude, ChatGPT, Cursor, or any AI agent via MCP.
Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.
An MCP server that provides web search capabilities powered by DeepSeek API, designed for AI assistants and agents.
Agent Skills
is a framework that dramatically improves LLM code agent output quality through structured pre-configuration.
48 agents · 35 frameworks · Research-first, AI-native, depth to the Mariana Trench · Solo founder Day 0 → IPO → public company
Opinionated, interactive health audit for a codebase. The skill scans the repo, forces a scope decision up front, then walks architecture, code quality, tests, performance, and dependencies.
Turn a (a URL from api.anthropic.com/v1/design/h/... or a local .tar.gz) into a written directly into your active Xcode workspace — built, previewed, and visually diff'd against the prototype until...
ClawMax provides a web-based platform to manage, monitor, and orchestrate OpenClaw AI agent teams. Deploy team templates, visualize workflow DAGs, track progress, and coordinate agents across your...
A Claude Code skill for a common problem: you want a second model (Codex) to apply the code while Claude preserves context for orchestration and judgment, and you don't want Codex grading its own...
船长AI视界：AI导演一键创作SKILL
Describe a materials problem in plain language. MatClaw writes the code, runs the simulation, and delivers results.
Turn your Flash model into a Pro. No model upgrade needed.
Build native-feeling macOS applications that look like Apple designed them.
阿里内网用户欢迎加群交流 【群号: 156800004200 / TMCP 天使用户群】
CodexOnAnyDevices enables you to keep vibe coding from your phone while working out at the gym. It runs on the web to control your Codex.