Jules MCP Server
Enables orchestration of multiple Jules AI workers for tasks like code generation, bug fixing, and review using the Google Jules API. It features git integration, a shared memory system, and real-time activity monitoring for complex, multi-agent development workflows.
README
<div align="center">
</div>
🗺️ Navigation
⚙️ Setup
Choose the installation method that fits your workflow. Both methods require a Jules API Key.
[!IMPORTANT] Visit jules.google.com/settings/api to generate your credentials before proceeding.
<details> <summary><b>🤖 Method 1: Agent-Driven Install (Recommended)</b></summary>
The fastest way to get started. Copy the block below and paste it into your AI assistant (Antigravity, Cursor, or Claude).
Read https://raw.githubusercontent.com/TheRealAshik/jules-mcp/main/docs/SELF_INSTALL.md and do as per the instructions. I have my JULES_API_KEY ready.
</details>
<details> <summary><b>👤 Method 2: Manual Self-Install</b></summary>
If you prefer to configure the server yourself, follow these steps:
-
Locate your config file:
- Antigravity:
~/.gemini/antigravity/mcp_config.json - Claude Desktop:
%APPDATA%\Claude\claude_desktop_config.json - Cursor: Settings > Features > MCP > Add New Server
- Antigravity:
-
Add the following snippet:
{
"mcpServers": {
"jules-mcp": {
"command": "npx",
"args": ["-y", "@realashik/jules-mcp"],
"env": {
"JULES_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
</details>
📖 Overview
Jules MCP is a high-performance Model Context Protocol (MCP) server designed to supercharge AI coding assistants. While standard AI agents are limited to linear task execution, Jules MCP introduces Staged Orchestration—enabling a "Commander" agent to deploy multiple specialized sub-agents (Maestros, Crews, Freelancers) to handle distinct parts of a project simultaneously or in sequence.
Built on top of the Google Jules API and the MCP SDK, it provides the bridge between your IDE and a distributed team of AI workers.
[!TIP] Jules MCP works best when allowed to manage its own branches. Ensure your
JULES_API_KEYhas repository write access for the best experience.
🚀 Features
<details> <summary><b>Click to expand features list</b></summary>
- 🎭 Multi-Role Orchestration: Spawn
MAESTRO(Architect),CREW(Implementer),FREELANCER(Specialist), orEVALUATOR(Quality Control). - 📝 Staged Workflows: Automatically manage git branches, code generation, and merging in a single, safe flow.
- 🧠 Global Shared Memory: Cross-session memory allows workers to pass variables and context like biological collaborators.
- 🛡️ Quality Enforcement: Built-in review cycles ensure code meets security and performance standards before merging.
- ⚡ Zero Configuration: Instantly usable via
npxwith automatic environment discovery. </details>
🛠 Development
# 1. Clone the repository
git clone https://github.com/TheRealAshik/jules-mcp.git
# 2. Install dependencies
npm install
# 3. Build & Run
npm run build
npm start
📂 Knowledge Base
- 🔧 SKILLS.md - Comprehensive tool mapping documentation.
- 🤖 SELF_INSTALL.md - Logic for AI agent self-installation.
🌟 Support
If Jules MCP helps you build faster, please consider:
- ⭐️ Starring the GitHub Repository
- 👤 Following TheRealAshik for updates.
Developed with ❤️ by TheRealAshik
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。