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 Model Completion Protocol (MCP) server implementation for ServiceNow, allowing Claude to interact with ServiceNow instances.
An Obsidian-native memory layer for your AI agent. Plain Markdown you own, in the same vault you already use.
Local-first MCP platform with OAuth2 for running and monitoring your servers
Operate Proxmox VE from MCP clients, AI agents, and OpenAPI tooling through one security-conscious control plane for VMs, LXCs, snapshots, backups, ISOs, container commands, and persistent...
Pro Tip: You can use this to ask your agent to export the 3d model directly into the project you are working on to use them in your app instantly. Demo
An MCP server that provides access to arXiv papers through their API.
An MCP proxy server that aggregates and serves multiple MCP resource servers through a single interface. This server acts as a central hub that can:
An MCP server that connects your AI assistant to HackerOne. It pulls your bug bounty history, program scopes, and report details into a local SQLite database, then exposes tools that let any...
MCP server for enabling LLM applications to perform deep research via the MCP protocol
MCP server for rendering Mermaid diagrams in Claude Code with functionality and a built-in skill for expert guidance.
An MCP server to use with AI agents such as OpenCode, Mai, VSCode, Claude, CLION, ...
An MCP server that automates WeChat on macOS using the Accessibility API and screen capture. It enables LLMs to interact with WeChat chats programmatically.
Agent Skills
The script. The prompt. The hosts' roles. Their voices. The content they discuss. All of it.
一个适用于 Claude Code / Codex 的技能，用来生成惊艳、带动画、单文件的 HTML 演示文稿，并内置浏览器编辑器：可拖拽对象、调整大小、编辑文本、重排页面、本地保存，并导出干净的独立 HTML。
新论文层出不穷，英文读得再顺也不如母语省心；我们想把这些论文变成排版规范、读着顺口的中文 PDF。
Drag-and-drop email editor for modern apps — source-available, MIT after two years
Swift Testing Agent Skill for AI Coding Assistants
Install and use the measurable adversarial code-audit skill with scan-only defaults and explicit permission before source edits.
从初稿搭建 · 结构修订 · 图文对齐 · 引用核验 · 投稿前预检 到 返修回复的全链路 journal-first · claim-driven · 证据边界优先
A compact agent skill for turning short prompts into beautiful, realistic GPT Image 2 images.
Direct complete videos—from the first idea to production-ready media.
Everything distilled from — a public X trader and AI/semiconductor supply-chain analyst known for tracing hyperscaler capex into upstream bottlenecks.
A production-ready OpenClaw plugin that implements the A2A (Agent-to-Agent) v0.3.0 protocol, enabling OpenClaw agents to discover and communicate with each other across servers — with zero-config...
SkVM is a compilation and runtime system that makes LLM agent skills portable across heterogeneous models and harnesses. It has four major parts: