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
The MCP Code Executor is an MCP server that allows LLMs to execute Python code within a specified Python environment.
AI-native SwiftUI component library with full-stack recipes — connect via MCP for instant access.
This Agent MCP allows you to train external intelligence with zero GPU and let you trade it at Tetrees EX
@cyanheads/git-mcp-server A Git MCP server for AI agents. STDIO & Streamable HTTP. 28 Tools · 1 Resource · 1 Prompt
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
Each RAG component was sharpened on its own, then folded into one repository: multi-identity auth, observability and systemd supervision come with it.
An MCP server for reading, searching, organizing, and sending email through IMAP and SMTP.
AI-native GPU frame debugging for RenderDoc English | 简体中文
一个基于 mcp-go 框架构建的 Go 服务，它提供了一个能动态生成 ECharts 图表页面的工具。
Give Claude Code eyes for your frontend. No more blind debugging where Claude guesses about your UI, you take screenshots, and you go back and forth hoping it understands what's broken.
Pure-Rust Android decompiler and security-audit suite. DEX → Java, Hermes → JavaScript. Cross-layer taint across the React Native bridge. CycloneDX SBOM + OpenVEX. CLI and MCP.
Datadog's managed MCP server connects your AI agents to Datadog's observability tools and data. Query logs, metrics, traces, incidents, and more - directly from your AI-powered dev tools.
Agent Skills
前阳光私募冠军基金经理、B站百大UP主的交易纪律，封装成可运行在真实行情上的 AI Skill。 基于 ~200 万字语料蒸馏，60+ 指标，30+ 战法，可回测可模拟、可自改进、可走完整闭环。
A collection of practical skill plugins for AI coding agents.
Skills that translate your coding agent's output into plain language: honest reports, straight verdicts, steps you can follow. MIT.
Portable operating instructions for AI agents controlling Android and iOS devices—locally or in the cloud.
面向硬件产品的PCB方案设计 AI Agent。输入产品需求，输出可评审、可落地的PCB原理图的方案。
Built from practice, not theory — calibrated against real deals including vLLM/Inferact ($150M @ $800M) and Hugging Face ($235M @ $4.5B).
OpenAI Codex CLI 0.128 introduced /goal — a persistent agent objective with runtime audit, token budget, and a soft-stop state machine. It can drive a single task for .
A framework for AI-First development with Claude Code and Codex. One methodology, two compatible runtimes.
为 OpenClaw / Pi AI Agent 打造的双引擎 Web 搜索技能。Grok AI + Tavily 双引擎交叉验证，纯 Shell 实现，零 MCP 依赖。
Make AI coding agents remember your project between sessions.
- 发布说明：v2.4.0 更新内容 - 官网更新历史：superdev.goder.ai/changelog
A practical library of , , and designed specifically for QA Automation Engineers, focusing on production-oriented solutions.