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
🚀 You're viewing the bleeding-edge dev docs! For other versions, check out the release/* branches.
Query OpenAI models directly from Claude using MCP protocol.
A currency conversion MCP server
DeepSeek Harness MCP Connector: connect servers, search tools across active connections, and troubleshoot discovery. Includes a continuously updated catalog; supports OAuth 2.
Android device bridge for Claude Code via MCP + Shizuku. No root, no model polling.
Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't guess.
Pure-Rust Android decompiler and security-audit suite. DEX → Java, Hermes → JavaScript. Cross-layer taint across the React Native bridge. CycloneDX SBOM + OpenVEX. CLI and MCP.
Python implementation for building Users Management Agent with MCP tools and MCP server
OnebotV11 Bot as MCP Server.
🍎 Mac (Apple Silicon) adaptation of baidu/Unlimited-OCR 6.7B VLM. .cuda()→.to('mps') patches + autocast workaround + MCP server. 20s/document on M4 Pro.
Autonomous DFIR agent — SANS SIFT Workstation MCP server for incident response
用 Claude Code 直接控制你的 TradingView 桌面版。讀圖、改圖、寫 Pine Script、跑晨間掃描——全部用對話完成。
Agent Skills
everything is topological chemputer!
akitaonrails' personal skills (not tailored for general usage)
Your open source AI CFO and Tax Accountant for individuals and businesses, inspired by Garry Tan's `gstack`
个人用的 Cursor Agent Skill 研究工具。在浏览器中加载、创建、导入 skill，并通过 Cursor SDK 运行 agent，可视化文件、执行结果与工具调用过程。
Empirically verified Nim coding skills.
Canonical example and migration guide for the Agent Plugins v1 specification.
Autonomous engineering organism — contract-first multi-agent team, 24/7 daemon, persistent memory, git-native safety, Guardian Swarm, MCP + A2A. | Builds production software, not prototypes.
Buffett-style company analysis skill for Codex that turns primary-source research into structured investment memos.
AI agent skills for production grade applications
Ship without fear. Proofs, not promises.
Security auditing CLI for AI agent skills - detects prompt injection, secrets, and dangerous code patterns.
A Codex Skill library built from McKinsey and BCG consulting methodologies, covering structured problem solving, MECE issue trees, hypothesis-driven analysis, strategy, operations, executive...