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
CLI and MCP server for discovering and calling Google APIs from agents and scripts.
Treegress Browser MCP is a Treegress-maintained fork of Playwright MCP. It exposes browser automation tools for MCP clients while delegating the snapshot and locator core to the Treegress Playwright...
Context Harness ingests external knowledge (files, Git repos, S3, Lua scripts) into a local SQLite store with optional embeddings, and exposes it via the ctx CLI and an MCP-compatible HTTP server so...
Interactive MCP App with an inline for get_task_status.
MCP server that gives AI assistants searchable access to MikroTik RouterOS documentation — 363 pages extracted live from MikroTik's official Docusaurus manual (https://manual.mikrotik.
Talk to your time tracking. Pull reports, start timers, inspect desktop activity, and turn raw Toggl data into useful recaps from Claude or any MCP-compatible client.
A production-ready iOS automation MCP server built with FastMCP 2.0, featuring clean modular architecture with complete platform segregation.
High Performance MCP server + client for Windows and macOS computer control built in Rust. Screenshot, mouse, keyboard, clipboard, and app management — all in-process via Rust NAPI.
MCP OCR module using macOS Vision framework
— automatically discover and configure MCP servers on your machine (remote or local).
Your AI agent doesn't know what's broken in production. This fixes that.
CLI toolkit for Dynamics 365 Finance & Operations X++ development. Indexes AOT metadata, scaffolds objects, and wires up AI agents via a stable JSON envelope and MCP.
Agent Skills
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.
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...
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。
Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.
ProductSpec is the open standard for product intent. It acts as a Product Harness for AI-native software work: what to build, what not to build, how to prove completion, and when intent changes.
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly. Instead of making language models reconstruct molecular structure from cryptic strings, MoleCode lets...
This guide is intended for anyone with zero or a small background in programming, AI, or machine learning who wants to become a strong AI engineer in 2026.
仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。議事録・調査レポート・社内ガイド・リサーチメモ・スライド構成といった仕事の文書から、note・ブログ・エッセイまで扱います。
Skills, rules, and validation hooks that teach AI coding agents to generate correct UdonSharp code
(As usual, XKCD has a comic for this. Appropriately enough, the comic is out of date.)
Science Superpowers is a complete computational-science methodology for your research agents, built on a set of composable skills plus initial instructions that make sure your agent actually uses...
Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦