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

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Things.app MCP Server

162 MCP tools for AI-powered Godot 4 development. Scene, animation, 3D, physics, particles, audio, shader, input simulation, runtime analysis, navigation, testing & more. $15 one-time.

MCP server exposing SSH control for Linux servers via Model Context Protocol.

Local-first Apple Health MCP server. Lets AI assistants answer questions about your sleep, workouts, activity and heart data from a local export.

MCP Server for interacting with Salesforce instances

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

Search Airbnb using your AI Agent

MCP Server for YouTube API, enabling video management, Shorts creation, and advanced analytics

An SDK building Laravel MCP servers

This repository contains Model Context Protocol (MCP) servers that enable MCP clients (like Claude Desktop or the cline.bot VS Code extension) to access Google's security products and services:

AI-powered travel hacking with points, miles, and award flights. Drop-in skills and MCP servers for OpenCode, Claude Code, and Codex.
Agent Skills

is an open-source, cloud-native vector database that stores both objects and vectors, enabling semantic search at scale.

A collection of interesting libraries and tools for Avalonia project.

Xiaomi Miloco

Codex-first, vendor-neutral RTL coding and verification skill using open-source tools

no-mistakes puts a local git proxy in front of your real remote. Push to no-mistakes instead of origin, and it spins up a disposable worktree, runs an AI-driven validation pipeline, forwards the...

Open source alternative to Semrush and Ahrefs

Stage-aware security skills for Codex that surface planning gaps, offer opt-in reviews, and help teams ship safer code without pretending to certify security.

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

The first UI framework for the agentic era — tiny, performant, with WASM sandboxes for safe code execution.

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and...

A multi-model AI workspace for Claude Code & Codex, featuring orchestration, realtime voice, and end-to-end encryption.

Fully Open Framework for Democratized Multimodal Training