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
一个将ACE(Augment Context Engine) 做成MCP的项目
Token-efficient MCP adapter for Pi coding agent
JSReverser-MCP 是一个面向 JavaScript 逆向分析的 MCP 工具，专门用于帮助开发者在真实浏览器环境中高效定位前端核心逻辑。它 将脚本检索、断点调试、函数 Hook、网络请求追踪、调用链分析、混淆还原和风险评估整合为统一能力，可直接接入 Claude、 Codex、Cursor 等支持 MCP 的客户端。
Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
This MCP server integrates with your Google Drive and Google Sheets, to enable creating and modifying spreadsheets.
MCP server that gives AI assistants the power to control a web browser.
Not a path. Not a URL. A handoff that answers back.
CodeGraph transforms your entire codebase into a semantically searchable knowledge graph that AI agents can actually reason about—not just grep through.
📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.
Citra — PDF answers with page-level proof. Local-first structured text, tables, OCR, visual evidence, and citations via MCP, CLI, and SDK.
Indexes any codebase into a structural knowledge graph — every dependency, call chain, cluster, and execution flow.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action...
Agent Skills
Agent skills extracted from real work. Each one shipped something first.
Personal Codex skills (drop-in folders under ~/.agents/skills/). Catalog: https://jmerta.github.io/codex-skills/
Open the interactive guide to learn more about the Skill
The open agent skills tool - npx skills
A curated list of essential skills, tools, and resources for building and enhancing advanced AI agents.
Keep your skills sharp. Intelligence for agent context.
Chainstack is the leading suite of services connecting developers with Web3 infrastructure
A structured Agent workflow for CUMCM, MCM/ICM, and Diangong Cup — designed to keep a 72–96 hour modeling project coherent from the first decision to the final submission.
会话 · 聊天记录 · 搜索 · 联系人 · 群成员 · 群昵称 · 收藏 · 统计 · 导出
🧠 plan · 🔨 implement · 🔍 review · ✅ QA gate · 🚢 merge Thirty-five agent skills that run a full PR pipeline. Install them into any repo, with any coding agent.
for creating, directing, validating, and delivering image, video, audio, voice, music, 3D, avatar, and interactive media.
Running 5 AI agents in parallel is easy. Making them not break each other's code is the hard part.