Jules MCP Server

Orchestrate multiple Jules AI workers for complex development workflows.

README.md

⚠️ Deprecated Notice

Jules MCP is now deprecated. Google Labs has released their official Jules SDK with native Model Context Protocol (MCP) support, making this community package obsolete.

πŸ—ΊοΈ Navigation


βš™οΈ 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.

πŸ€– Method 1: Agent-Driven Install (Recommended)

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/refs/heads/main/docs/AGENT_INSTALL.md and do as per the instructions.
πŸ‘€ Method 2: Manual Self-Install

If you prefer to configure the server yourself, follow these steps:

  1. 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
  2. Add the following snippet:

{
  "mcpServers": {
    "jules-mcp": {
      "command": "npx",
      "args": ["-y", "@realashik/jules-mcp"],
      "env": {
        "JULES_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

πŸ“– Overview

Jules MCP is a Model Context Protocol (MCP) server designed to supercharge AI coding agents to control Jules. While standard AI agents are limited to linear task execution, Jules MCP introduces Staged Orchestrationβ€”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 official @google/jules-sdk, it provides the bridge between your IDE and a distributed team of AI workers with advanced features like real-time streaming, session management, and intelligent caching.

[!TIP] Use IDE agents to analyse and assign tasks to Jules to get best output from this MCP.

[!NOTE] v1.0.4+ now uses the official Google Jules SDK for improved reliability, streaming support, and better error handling.


πŸš€ Features

Click to expand features list
  • 🎭 Multi-Role Orchestration: Spawn MAESTRO (Architect), CREW (Implementer), FREELANCER (Specialist), or EVALUATOR (Quality Control).
  • πŸ“ 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.
  • πŸ›‘οΈ Quality Enforcement: Built-in review cycles ensure code meets security and performance standards before merging.
  • ⚑ Zero Configuration: Instantly usable via npx with automatic environment discovery.
  • 🌊 Real-time Streaming: Stream live activity updates from Jules sessions using the official SDK.
  • πŸ”„ Session Management: Simplified session lifecycle with automatic polling and state management.

🌟 Support

If Jules MCP helps you build faster, please consider:

Developed with ❀️ by TheRealAshik

Environment Variables

JULES_API_KEYrequiredAPI key for authenticating with the Google Jules API

Try it

β†’Deploy a MAESTRO agent to architect the new authentication module.
β†’Assign a CREW agent to implement the bug fixes identified in the last review.
β†’Run an EVALUATOR agent to check the current codebase for security and performance standards.
β†’Coordinate a FREELANCER agent to specialize in refactoring the database connection logic.

Frequently Asked Questions

What are the key features of Jules MCP?

Multi-Role Orchestration of MAESTRO, CREW, FREELANCER, and EVALUATOR agents. Staged workflows for managing git branches and code generation. Global shared memory for cross-session variable and context passing. Real-time activity streaming using the official Google Jules SDK. Automated quality enforcement and review cycles.

What can I use Jules MCP for?

Managing complex multi-agent development workflows in an IDE. Automating code generation and merging tasks in a single safe flow. Enforcing security and performance standards through automated review cycles. Passing context and variables between different AI worker sessions.

How do I install Jules MCP?

Install Jules MCP by running: npx -y @realashik/jules-mcp

What MCP clients work with Jules MCP?

Jules MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Jules MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Open Conare