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
MCP server for Hugging Face dataset viewer
Vendor-neutral MCP configuration manager with first-class Claude Code support.
Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.
MCP Server for the Mattermost API, enabling Claude and other MCP clients to interact with Mattermost workspaces.
Contemplative reasoning MCP server — Lotus Sutra wisdom framework with interactive ext-apps journey visualization.
If it's on the screen, it's an API. Control any desktop app through JSON. REST API + MCP server. Single binary. Zero dependencies.
An MCP server for the Rootly API for Cursor, Windsurf, Claude, and other MCP clients.
A Node.js server that uses FFmpeg to manipulate video files. This server provides APIs to:
Detonate files & URLs in cloud malware sandboxes (Hybrid Analysis, tria.ge, ANY.RUN) and enrich IOCs across MalwareBazaar, ThreatFox, URLhaus, Feodo, URLScan & VirusTotal — straight from Claude.
MCP implementation of parliamentary APIs, including Hansard and Members APIs
The most comprehensive MCP server for Meta's business platform. 200+ tools covering Facebook Pages, Instagram, Threads, Ads Manager, Commerce, Conversions API, Audiences, Insights, and Ad Library.
Plugins for the OutSystems remote MCP.
Agent Skills
一句话：输入一个基金代码，Agent 把基金经理 8 年的每一笔买卖翻出来，拿 12 个月后的真实走势逐笔验对错，最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测，全都有。
- Manage Claude Code, OpenAI Codex, Google Gemini, OpenCode, and custom AI agents from one powerful command-line interface.
(As usual, XKCD has a comic for this. Appropriately enough, the comic is out of date.)
中文内部技术写作的 agent skill。约束设计文档、评审稿、postmortem、分享稿等场景的语气、句法、结构，让产出贴近技术汇报，避开营销稿和散文气质。
LeetCode Helper is a Codex skill for solving LeetCode-style coding interview problems with optimized solutions and detailed explanations.
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .
Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
agnix Lint agent configurations before they break your workflow
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
Everything you need to know about OpenCode — from your first prompt to custom agents, skills, plugins, and MCP integrations.