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-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB.
Access Kagi search and summarizer via session tokens — completely free. Works with Claude Desktop, Cursor, Windsurf, Cline, Hermes and any MCP-compatible AI coding assistant/agent.
CLI, OpenAI-compatible API, Chrome extension bridge, and MCP server for Google Flow image and video generation.
One config to rule them all. Practical standard layer for multi-LLM development.
VV knowledge layer for AI agents — MCP server exposing Visualize Value frameworks, voice, and content
Maybe the headless Ghidra MCP you are looking for.
Security review mascot logo for the DocSentinel console and documentation.
MCP server for build123d to improve AI cognition when creating 3D CAD models
MCP Slim Guard gives a host one deliberate way to reach authorized upstream tools. It keeps input schemas intact, validates calls before the upstream is invoked, and can recover an oversized result...
An MCP server that provides integration between Neo4j graph database and Claude Desktop, enabling graph database operations through natural language interactions.
A lightweight, zero-footprint TypeScript MCP server that lets AI assistants drive the Godot 4.x game engine.
The server implements a few of the Coinmarket API endpoints - Custom coinmarket:// URI scheme for accessing individual notes - Each note resource has a name, description and text/plain mimetype
Agent Skills
Watchmen turns every coding session into the skill bundles you’d never sit down and write yourself.
: Claude Opus 5 (claude-opus-5) / Claude Opus 4.6 (earlier chapters) : Claude Code + OpenClaw + OpenCode : 2026-08-02 : v2026.3.9 (v2026.3.8-170-g665f67726) : https://github.
Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness.
░█░█░█▀█░█▀█ ░█▀▄░█░█░█░█ ░▀░▀░▀▀▀░▀░▀ Minimal coding agent harness
Built from practice, not theory — calibrated against real deals including vLLM/Inferact ($150M @ $800M) and Hugging Face ($235M @ $4.5B).
Portable operating instructions for AI agents controlling Android and iOS devices—locally or in the cloud.
OpenAI Codex CLI 0.128 introduced /goal — a persistent agent objective with runtime audit, token budget, and a soft-stop state machine. It can drive a single task for .
Open-source repository of finance and investing skills built around the SKILL.md format.
skill infrastructure for multi-agent projects
A design skill for building never-cheap, high-craft web interfaces — both brand surfaces and product UI.
A systematic methodology for refactoring AI-generated code (Vibe Coding). Helps you discover duplicate implementations, unused resources, and inconsistent patterns.
A practical library of , , and designed specifically for QA Automation Engineers, focusing on production-oriented solutions.