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
Local code search for AI coding agents: a CLI and MCP server with hybrid keyword + semantic search and SQL relevance-ranked aggregation over an index in plain files. No accounts, no keys, no server.
Keeping up with AI trends is exhausting. Claude doesn't know what happened after its training cutoff. Ask it "what's hot in AI right now?" and you get stale answers.
Stdio MCP server for sandboxed file access — read files, search content, safely edit with checksums, and manage file structure.
Install and configure MCP servers across all major AI clients with one command.
基于 的增强版本，通过**显著减少对 Figma API 的请求次数，从而缓解速率限制问题，提升稳定性与响应速度。
A specialized MCP server that bridges Neo4j graph database with AI agents, providing memory-focused tools for storing, recalling, and connecting information in a knowledge graph.
Relay beside your IDE — the agent pauses, you review & answer, it continues. All in one tools/call .
This is an MCP Server that wraps various JVM diagnostic tools (CLI) such as jstat, jcmd, jps, adds a nice prompt to improve how they work, and exposes them.
An MCP server that provides KOSPI/KOSDAQ stock data from KRX Data Marketplace.
A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Protocol — for most features.
Burp MCP proxy with compression pipeline — reduces 182KB responses to ~4KB
CLI-first MCP server for composer-based Kirby CMS projects — inspect blueprints/templates/plugins, interact with a real Kirby runtime, and use a bundled Kirby knowledge base.
Agent Skills
Vercel's official collection of agent skills
that teach AI assistants how to build fast, beautiful, secure Mapbox applications across platforms. Covers performance optimization, cartographic design, framework integration, platform migration,...
AI agents should not give project advice from vibes.
Skills for AI coding agents — Laravel, PHP, React, TypeScript, testing, security, and code quality.
Running 5 AI agents in parallel is easy. Making them not break each other's code is the hard part.
A curated, hands-on library of notebooks, demos, and resources for AI/ML, Deep Learning, Generative AI, AI-Agents, fine-tuning, and modern tooling.
for creating, directing, validating, and delivering image, video, audio, voice, music, 3D, avatar, and interactive media.
🧠 plan · 🔨 implement · 🔍 review · ✅ QA gate · 🚢 merge Thirty-five agent skills that run a full PR pipeline. Install them into any repo, with any coding agent.
A structured Agent workflow for CUMCM, MCM/ICM, and Diangong Cup — designed to keep a 72–96 hour modeling project coherent from the first decision to the final submission.
Chainstack is the leading suite of services connecting developers with Web3 infrastructure
Agent skills I use every day.
Open the interactive guide to learn more about the Skill