Gemini CLI MCP Async Server

Asynchronous MCP wrapper for Gemini CLI

Enable Claude Code to spawn child Gemini CLI sessions for parallel task execution.

Features

• ✅ Async execution - Start tasks in background, continue working

• ✅ Multi-instance parallelism - Run multiple Gemini CLI sessions simultaneously

• ✅ Automatic cleanup - No zombie processes

• ✅ Zero config - Works out of the box

Quick Start

🚀 Install with UVX

Zero configuration - just run:

uvx gemini-cli-mcp-async

Configure Claude Code or other MCP Client

Add to your ~/.claude/settings.json:

{
  "mcpServers": {
    "gemini-cli-mcp": {
      "command": "uvx",
      "args": ["gemini-cli-mcp-async"],
      "env": {}
    }
  }
}

Restart Claude Code

Reload or restart Claude Code to load the MCP server.

Usage Examples

🚀 Async Execution (Game Changer!)

Start a long task and continue working immediately:

You:

Please analyze the entire project code and generate a comprehensive technical report

Claude: I'll analyze your entire project and generate a technical report. This is a large task, so I'll start it asynchronously...

✅ Task Started (Task ID: abc12345) You can continue working on other things while it runs in the background!

You: (Continue working immediately)

While the report is generating, help me write some unit tests

Claude: Sure! Let me write those unit tests for you...

You: (A few minutes later)

Can you check if the report task is finished?

Claude: ✅ Report Complete!

[View Detailed Technical Report]

• Project structure analysis

• Code quality assessment

• Performance optimization recommendations

• Security audit results

⚡ Parallel Execution

Run multiple tasks simultaneously:

You:

I need to do three things at once:

1. Generate unit tests for utils.py

2. Refactor database.py to use async/await

3. Add type hints to all functions in api.py

Claude: I'll start all three tasks in parallel!

🔄 Task 1 Started (Task ID: task1) - Generating unit tests 🔄 Task 2 Started (Task ID: task2) - Refactoring database code 🔄 Task 3 Started (Task ID: task3) - Adding type hints

All tasks are running in parallel...

You: (Later)

Are all three tasks finished?

Claude: ✅ All Complete!

• ✅ Task 1: Unit tests for utils.py generated

• ✅ Task 2: database.py refactored to async mode

• ✅ Task 3: Type hints added to api.py functions

🎯 Quick Sync Tasks

For simple immediate tasks:

You:

Write a Python function to validate email addresses

Claude:

import re

def validate_email(email):
    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
    return re.match(pattern, email) is not None

# Usage examples
print(validate_email("user@example.com"))  # True
print(validate_email("invalid-email"))    # False

✅ Task Complete!

Why Async?

Problem: Gemini CLI blocks the parent session while running.

Solution: This MCP server spawns child Gemini CLI processes that run in the background.

Benefits:

• 🚀 Start a task and continue working immediately

• ⚡ Run multiple tasks in parallel

• 🎯 No blocking, no waiting

• 🧹 Automatic process cleanup

API Reference

gemini_cli_execute(query, working_dir, sandbox, yolo, approval_mode, experimental_acp, allowed_mcp_server_names, allowed_tools, extensions, include_directories, output_format, screen_reader, debug, additional_args, timeout)

Execute Gemini CLI synchronously and return result immediately.

gemini_cli_execute_async(query, working_dir, sandbox, yolo, approval_mode, experimental_acp, allowed_mcp_server_names, allowed_tools, extensions, include_directories, output_format, screen_reader, debug, additional_args)

Start Gemini CLI task in background and return task_id.

gemini_cli_check_result(task_id)

Check status of async task and return result if completed.

Configuration

All Gemini CLI parameters are supported. Key options:

• sandbox - Enable sandbox mode

• yolo - Auto-confirm prompts

• approval_mode - Set approval mode ('default', 'auto_edit', 'yolo')

• output_format - Output format ('text', 'json', 'stream-json')

• timeout - Timeout for sync execution (seconds)

• debug - Enable debug logging

Troubleshooting

Server not showing up?

• Use absolute path in config

• Run: chmod +x gemini_cli_mcp_async_server.py

• Restart Claude Code

Task stuck in "running"?

• Wait a moment, large tasks take time

• Check: ls -la /tmp/gemini_cli_tasks/

• View logs: tail -f /tmp/gemini_cli_mcp_debug.log

No output from long tasks:

• Use output_format="stream-json" for better output capture

• Check disk space in /tmp

Requirements

• Python 3.8+

• uvx

• Gemini CLI installed

License

MIT License

Questions? Open an issue on GitHub.