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

codespelunker - CLI code search tool that understands code structure and ranks results by relevance. No indexing required with CLI, TUI, MCP and HTTP support.

Integrate QuantConnect's research environment, statistical analysis, and portfolio optimization into your AI workflows. Locally hosted, secure & capable of dramatically improving productivity

An open-source Model Context Protocol server that gives AI agents (Claude, ChatGPT, Cursor, and others) direct read/write access to Sitecore.

Geocoding MCP server with GeoPY!

A Model Context Protocol server implementation for interacting with Salesforce through its REST API using jsforce.

A specialized MCP server for Payload CMS 3.0 Validate code, generate templates, and scaffold projects following best practices

mcpr is an R implementation of the Model Context Protocol (MCP), enabling R applications to expose capabilities (tools, resources, and prompts) to AI models through a standard JSON-RPC 2.0 interface.

A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

A clojure-sdk for creating Model Context Protocol servers!

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation,...

Compose, manage, and run MCP servers as Docker containers. With a Unified API gateway built in.

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Agent Skills

pixel-asset-master-skills 是一套2D 像素游戏资产生成专业技能体系与标准化工作流框架。 内置完整流水线规范、多角色协作执行机制、项目目录规约、像素尺寸 / 配色板 / 精灵模板库,集成项目初始化、风格选定、参数六维确认、像素素材生成、帧动画序列制作、资产质检、后处理、精灵图集打包与多格式导出全链路能力。

Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and...

OTel Plugin for Hermes Agent

华创金工形态学Skill

微信读书前几天上了一个官方 AI skill(weread.qq.com/r/weread-skills),把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强,但它只是「自然语言包装的搜索接口」——你让它推荐书,它不会去看你已经读过什么,常把你笔记 68 条的书又当新书推回来给你。

For engineers who want agents shipping code without a human in the loop.

A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...

Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升,一个现实需求也逐渐显现:面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程,希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。

Human-defined workflows. AI-powered execution. YAML decision trees with scheduling, hooks, MCP, and 21 built-in tools.

There are plenty of skills out there. This library avoids slop and only ships skills that:

Azur Lane Resources extracted and parsed by Fernando2603/Azurex

面向研究人员的边界核对工作流:在使用 AI、OCR、文献工具或云服务处理研究材料前,整理权限、隐私、来源/可追溯性、机构审批和保留期限问题。