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
playwright-dotnet-mcp
is a next-generation agent orchestration framework that enables intelligent agents to control and coordinate actions across creative and technical tools in real time using the .
A Model Context Protocol (MCP) server that allows Claude Desktop to perform document operations on Microsoft Word, Excel, and PDF files.
Model Context Protocol (MCP) server for Emacs. Enables generating and running elisp code in a running Emacs process.
BGG MCP provides access to the BoardGameGeek API through the Model Context Protocol, enabling retrieval and filtering of board game data, user collections, and profiles.
MCP Server for Hex Package Versions
GUI for the Windows Subsystem for Linux — and native Linux/macOS VMs on Mac. Install, back up, move and configure distros without CLI flags; AI assistant with tools, MCP server for agents, remote WSL...
A Python-based Model Context Protocol (MCP) server that provides AI assistants like Claude with access to your Radarr (movies) and Sonarr (TV series) data.
A Model Context Protocol (MCP) server standalone CLI for querying PowerPlatform / Dataverse environments.
A Model Context Protocol (MCP) server for integrating ClickUp tasks with AI applications. This server allows AI agents to interact with ClickUp tasks, spaces, lists, and folders through a...
A server implementation for Wikidata API using the Model Context Protocol (MCP). This project provides tools to interact with Wikidata, such as (entity and property), (label and description) and .
An Model Context Protocol server for APIs, enabling AI agents (e.g. Cursor, Claude, LangChain) to securely query market data, place orders, and check positions and accounts.
Agent Skills
This repository provides a collection of composable Dockerfiles and build scripts for deploying and running software, full applications, and select demonstrators on AMD Ryzen AI hardware.
🧬 Darwinia Give your AI agent the power to evolve its own trading strategies. Trading agents that discover strategies through Darwinian selection and adversarial self-play — not human-written rules.
Why use many token when few token do trick?
小提示：导入数据时**，尽量不要用 JSON——多数微信导出工具的 JSON 是给 LLM 微调用的格式，没有时间戳，跑不出 K 线。详见 输入格式。
—— 一套可被任意 AI agent（Claude / GPT / Cursor…）使用的**。
面向 AI Agents 的安全、可持久化沙箱执行平台（Secure, Persistent Execution Platform for AI Agents）
Your future self will thank you. Or blame you. It depends on the diff.
TL;DR: Thea brings coding agents to the physical world.
A Claude Code plugin that audits your mobile app against store review policies — the store rejects it.
A grab-bag of experimental transformer kernels and utilities (mostly PyTorch + Triton).
10 agentes (8 de núcleo, Selina si hay frontend y Lucius bajo demanda), catálogo de 11 skills de proceso, memoria persistente de decisiones por proyecto, 6 flujos de trabajo con quality gates...
Most research-idea workflows fail in one of three ways: