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
A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.
MCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.
Terminal-first Instagram analytics, downloads, and MCP tools powered by HikerAPI, OpenRouter, and FastMCP.
A Local add-on that provides an MCP server and project context for AI-powered WordPress development. Works with Claude Code, Cursor, Windsurf, VS Code Copilot, and any MCP client.
面向 NetEase Minecraft / Bedrock 开发场景的通用 MCP Server。
██╗ ██╗██╗███████╗██╗ ██████╗ ███╗ ██╗ ██║ ██║██║██╔════╝██║██╔═══██╗████╗ ██║ ██║ ██║██║███████╗██║██║ ██║██╔██╗ ██║ ╚██╗ ██╔╝██║╚════██║██║██║ ██║██║╚██╗██║ ╚████╔╝ ██║███████║██║╚██████╔╝██║...
A command-line interface for MCP servers. curl for MCP.
The LuxAlgo ecosystem as MCP tools: free and keyless.
Find and call JustOneAPI endpoints from MCP-compatible AI assistants using natural language.
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
youtube transcriber mcp server
An MCP server that enables searching for Rust crates and their documentation from crates.io and docs.rs.
Agent Skills
Installation | View Demo | Quick Start | Commands | Contribute
🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.
Eleven Claude Code skills, ported to OpenCode. Code review, security audit, feature dev, frontend design, and the rest of the kit — installable in one line.
An explainable, cautious AI-generated text risk analyzer for coding agents and local workflows.
Skills based on the Layered Rails book and beyond
Personal AI assistant built on agentsdk-go.
A file-backed, spec-driven AI coding workflow framework for building real software while staying in control.
默认启用 26 个数据源 · LLM 摘要 · 21 个股票/加密标的** · 中英双语 · 6 个 LLM 后端可选。 ： · · 。
终端里起多个会话并行干活、互相通信；长任务跑着的时候人走开了，也能从微信/企微把它喊回来。
Science is dying because the human is in the way. Not through malice. Not through stupidity. Through the structural limitations of a cognitive architecture that evolved to track prey on a savanna,...
High-performance personal AI assistant in C++17
基于 Hermes 改造的轻量级 AI 助手框架，可以快速打造商用 SaaS 平台，支持多租户隔离部署、多平台渠道接入、工具调用、定时任务和 Web 实时通信。