Skip to main content
Glama

Gemini CLI MCP Server

by orzcls

πŸš€ Gemini MCP Tool - Windows Fixed Version

npm version License: MIT

Latest Version v1.0.21 - Fixed cross-terminal compatibility issues and fetch-chunk format errors

A Windows-compatible Model Context Protocol (MCP) server that enables AI assistants to interact with Google's Gemini CLI. This is a fixed version specifically designed to work seamlessly on Windows environments with PowerShell support.

Note: This is an enhanced version of the original gemini-mcp-tool with Windows-specific fixes and improvements.

πŸ†• Latest Updates (v1.0.21)

  • πŸ”§ Fixed Cross-Terminal Compatibility - Resolved Node.js path not found issues in different terminal environments

  • πŸ“¦ Fixed fetch-chunk Format Error - Fixed MCP protocol format mismatch in chunked responses

  • πŸ›‘οΈ Enhanced PATH Environment Variable Handling - Automatically adds common Node.js installation paths

  • βœ… Full Compatibility with All Terminals - Supports PowerShell, CMD, VS Code Terminal, Trae AI, CherryStudio, etc.

  • πŸš€ Improved Error Handling - Better error messages and debug output

v1.0.3 Updates

  • πŸ†• PowerShell Path Parameter Support - Added optional powershellPath parameter allowing users to customize PowerShell executable path

  • βœ… Fixed PowerShell Execution Error - Resolved spawn powershell.exe ENOENT issue

  • βœ… Improved Windows Compatibility - Automatic detection of available PowerShell versions

  • βœ… Fixed Undefined Variable Error - Fixed args variable issue in executeCommandWithPipedInput function

  • βœ… Enhanced Error Handling - Better error messages and debug output

  • βœ… Backward Compatibility - Existing configurations require no modification, automatically uses default detection logic

✨ Features

  • πŸͺŸ Windows Compatible: Full PowerShell support with Windows-specific path handling

  • πŸ“Š Large Context Window: Leverage Gemini's massive token window for analyzing entire codebases

  • πŸ“ File Analysis: Analyze files using @filename syntax

  • πŸ”’ Sandbox Mode: Safe code execution environment

  • πŸ”— MCP Integration: Seamless integration with MCP-compatible AI assistants (Trae AI, Claude Desktop)

  • ⚑ NPX Ready: Easy installation and usage with NPX

  • πŸ”§ Environment Variable Support: Flexible API key configuration

This Windows-fixed version resolves:

  • PowerShell parameter passing issues

  • Character encoding problems with Chinese/Unicode text

  • Command line argument escaping on Windows

  • Environment variable handling

πŸ“‹ Prerequisites

Before using this tool, ensure you have:

  1. Node.js (v16.0.0 or higher)

    node --version # Should be v16+
  2. Google Gemini CLI installed and configured

    npm install -g @google/generative-ai-cli # Verify installation gemini --version
  3. API Key: Get your API key from Google AI Studio

πŸ“¦ Installation

Quick Start with NPX (Recommended)

# Use latest version (recommended) npx gemini-mcp-tool-windows-fixed@1.0.21 # Or use latest version tag npx -y gemini-mcp-tool-windows-fixed@latest

Global Installation

# Install latest version npm install -g gemini-mcp-tool-windows-fixed@1.0.21 # Run the tool gemini-mcp-tool-windows-fixed

Updating Existing Installation

If you previously installed an older version:

# Uninstall old version and install latest npm uninstall -g gemini-mcp-tool-windows-fixed npm cache clean --force npm install -g gemini-mcp-tool-windows-fixed@1.0.21

βš™οΈ MCP Client Configuration

Claude Code (One-Line Setup)

# One-command setup for Claude Code claude mcp add gemini-cli -- npx -y gemini-mcp-tool-windows-fixed@1.0.21

Verify Installation: Type /mcp inside Claude Code to verify the gemini-cli MCP is active. 1

Alternative: Import from Claude Desktop

If you already have it configured in Claude Desktop:

  1. Add to your Claude Desktop config (see below)

  2. Import to Claude Code:

    claude mcp add-from-claude-desktop

Trae AI (Recommended)

  1. Open: %APPDATA%\Trae\User\mcp.json

  2. Add this configuration:

{ "mcpServers": { "gemini-cli": { "name": "gemini-cli", "description": "Windows-compatible Gemini MCP Tool", "baseUrl": "", "command": "npx", "args": [ "-y", "gemini-mcp-tool-windows-fixed@1.0.21" ], "env": { "GEMINI_API_KEY": "YOUR_ACTUAL_API_KEY_HERE" }, "isActive": true, "providerUrl": "https://github.com/orzcls/gemini-mcp-tool-windows-fixed" } } }

Claude Desktop

  1. Open: %APPDATA%\Claude\claude_desktop_config.json

  2. Add this configuration:

{ "mcpServers": { "gemini-cli": { "command": "npx", "args": ["-y", "gemini-mcp-tool-windows-fixed@1.0.21"], "env": { "GEMINI_API_KEY": "YOUR_ACTUAL_API_KEY_HERE" } } } }

πŸ”‘ API Key Configuration

Option 1: MCP Configuration (Recommended)

Replace YOUR_ACTUAL_API_KEY_HERE in the configuration above with your actual API key.

Option 2: Environment Variable

# Temporary (current session) $env:GEMINI_API_KEY = "your-actual-api-key" # Permanent (user level) [Environment]::SetEnvironmentVariable("GEMINI_API_KEY", "your-actual-api-key", "User") # Verify echo $env:GEMINI_API_KEY

Configuration File Locations

Claude Desktop:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Linux: ~/.config/claude/claude_desktop_config.json

Trae AI:

  • Windows: %APPDATA%\Trae\User\mcp.json

πŸ› οΈ Available Tools

This MCP server provides the following tools for AI assistants:

1. ask-gemini

Interact with Google Gemini for analysis and questions.

Parameters:

  • prompt (required): The analysis request. Use @ syntax for file references

  • model (optional): Gemini model to use (default: gemini-2.5-pro)

  • sandbox (optional): Enable sandbox mode for safe code execution

  • changeMode (optional): Enable structured change mode

  • chunkIndex (optional): Chunk index for continuation

  • chunkCacheKey (optional): Cache key for continuation

2. brainstorm

Generate creative ideas using various brainstorming frameworks.

Parameters:

  • prompt (required): Brainstorming challenge or question

  • model (optional): Gemini model to use

  • methodology (optional): Framework (divergent, convergent, scamper, design-thinking, lateral, auto)

  • domain (optional): Domain context (software, business, creative, etc.)

  • constraints (optional): Known limitations or requirements

  • existingContext (optional): Background information

  • ideaCount (optional): Number of ideas to generate (default: 12)

  • includeAnalysis (optional): Include feasibility analysis (default: true)

3. fetch-chunk

Retrieve cached chunks from changeMode responses.

Parameters:

  • cacheKey (required): Cache key from initial response

  • chunkIndex (required): Chunk index to retrieve (1-based)

4. timeout-test

Test timeout prevention mechanisms.

Parameters:

  • duration (required): Duration in milliseconds (minimum: 10ms)

5. ping

Test connection to the server.

Parameters:

  • prompt (optional): Message to echo back

6. Help

Display help information about available tools.

🎯 Usage Examples

Once configured, you can use the following tools through your MCP client:

Natural Language Examples 2

With File References (using @ syntax):

  • "ask gemini to analyze @src/main.js and explain what it does"

  • "use gemini to summarize @. the current directory"

  • "analyze @package.json and tell me about dependencies"

General Questions (without files):

  • "ask gemini to search for the latest tech news"

  • "use gemini to explain div centering"

  • "ask gemini about best practices for React development related to @file_im_confused_about"

  • "use gemini to explain index.html"

  • "understand the massive project using gemini"

  • "ask gemini to search for latest news"

Using Gemini CLI's Sandbox Mode (-s): 2 The sandbox mode allows you to safely test code changes, run scripts, or execute potentially risky operations in an isolated environment.

  • "use gemini sandbox to create and run a Python script that processes data"

  • "ask gemini to safely test @script.py and explain what it does"

  • "use gemini sandbox to install numpy and create a data visualization"

  • "test this code safely: Create a script that makes HTTP requests to an API"

Slash Commands (for Claude Code Users) 2

You can use these commands directly in Claude Code's interface (compatibility with other clients has not been tested):

  • /analyze: Analyzes files or directories using Gemini, or asks general questions

    • prompt (required): The analysis prompt. Use @ syntax to include files (e.g., /analyze prompt:@src/ summarize this directory) or ask general questions (e.g., /analyze prompt:Please use a web search to find the latest news stories)

  • /sandbox: Safely tests code or scripts in Gemini's sandbox environment

    • prompt (required): Code testing request (e.g., /sandbox prompt:Create and run a Python script that processes CSV data or /sandbox prompt:@script.py Test this script safely)

  • /help: Displays the Gemini CLI help information

  • /ping: Tests the connection to the server

    • message (optional): A message to echo back

Available Tools

  • ask-gemini: Send prompts to Gemini

    "Explain how MCP works"
  • analyze-file: Analyze specific files using @filename syntax

    "Analyze @package.json and suggest improvements"
  • sandbox-mode: Execute code in a safe environment

    "Run this Python code in sandbox mode: print('Hello World')"

πŸ”§ Windows-Specific Fixes

This version includes the following Windows-specific improvements:

  1. PowerShell Parameter Handling: Fixed argument passing to avoid parameter splitting

  2. Character Encoding: Proper UTF-8 handling for Chinese and Unicode characters

  3. Quote Escaping: Correct escaping of quotes in command arguments

  4. Environment Variables: Improved .env file loading and environment variable handling

  5. Path Resolution: Windows-compatible path handling

πŸ§ͺ Testing Installation

1. Test Gemini CLI

gemini -p "Hello, how are you?"

2. Test MCP Tool

npx -y gemini-mcp-tool-windows-fixed # Should show: [GMCPT] Gemini CLI MCP Server (Fixed) started

3. Test MCP Integration

  1. Restart your MCP client (Trae AI, Claude Desktop)

  2. Try asking: "Use gemini to explain what MCP is"

  3. Check for successful responses

πŸ› Troubleshooting

Common Issues

"Command not found: gemini"

npm install -g @google/generative-ai-cli

"API key not found"

# Check if API key is set echo $env:GEMINI_API_KEY # Set if empty $env:GEMINI_API_KEY = "your-api-key"

"Permission denied"

# Check execution policy Get-ExecutionPolicy Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

For detailed troubleshooting, see INSTALL-GUIDE.md.

πŸ”§ Windows-Specific Fixes

This version includes several Windows-specific improvements:

  • PowerShell Integration: Native PowerShell command execution

  • Path Handling: Proper Windows path resolution

  • Environment Variables: Enhanced environment variable support

  • Error Handling: Better error messages for Windows environments

  • Dependency Management: Simplified dependency structure

🀝 Contributing

Contributions are welcome! Please:

  1. Fork the repository

  2. Create a feature branch

  3. Test on Windows environments

  4. Submit a pull request

πŸ“„ License

MIT License - see LICENSE file for details.

πŸ™ Acknowledgments

πŸ“ž Support

If you encounter any issues or have questions:

  1. Check the Issues page

  2. Create a new issue with detailed information about your problem

  3. Include your Windows version, Node.js version, and error messages


Made with ❀️ for Windows developers

Note: This is a Windows-optimized fork of the original gemini-mcp-tool. For other platforms, consider using the original version.

Deploy Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

local-only server

The server can only run on the client's local machine because it depends on local resources.

A Windows-compatible Model Context Protocol server that enables AI assistants to interact with Google's Gemini CLI, supporting file analysis, large context windows, and safe code execution.

  1. πŸ†• Latest Updates (v1.0.21)
    1. v1.0.3 Updates
  2. ✨ Features
    1. πŸ“‹ Prerequisites
      1. πŸ“¦ Installation
        1. Quick Start with NPX (Recommended)
        2. Global Installation
        3. Updating Existing Installation
      2. βš™οΈ MCP Client Configuration
        1. Claude Code (One-Line Setup)
        2. Alternative: Import from Claude Desktop
        3. Trae AI (Recommended)
        4. Claude Desktop
      3. πŸ”‘ API Key Configuration
        1. Option 1: MCP Configuration (Recommended)
        2. Option 2: Environment Variable
        3. Configuration File Locations
      4. πŸ› οΈ Available Tools
        1. 1. ask-gemini
        2. 2. brainstorm
        3. 3. fetch-chunk
        4. 4. timeout-test
        5. 5. ping
        6. 6. Help
      5. 🎯 Usage Examples
        1. Natural Language Examples <mcreference link="https://github.com/jamubc/gemini-mcp-tool" index="2">2</mcreference>
        2. Slash Commands (for Claude Code Users) <mcreference link="https://github.com/jamubc/gemini-mcp-tool" index="2">2</mcreference>
        3. Available Tools
      6. πŸ”§ Windows-Specific Fixes
        1. πŸ§ͺ Testing Installation
          1. 1. Test Gemini CLI
          2. 2. Test MCP Tool
          3. 3. Test MCP Integration
        2. πŸ› Troubleshooting
          1. Common Issues
        3. πŸ”§ Windows-Specific Fixes
          1. 🀝 Contributing
            1. πŸ“„ License
              1. πŸ™ Acknowledgments
                1. πŸ“ž Support

                  Related MCP Servers

                  • -
                    security
                    F
                    license
                    -
                    quality
                    A server implementing the Model Context Protocol that enables AI assistants like Claude to interact with Google's Gemini API for text generation, text analysis, and chat conversations.
                    Last updated -
                    • Linux
                    • Apple
                  • -
                    security
                    A
                    license
                    -
                    quality
                    A Model Context Protocol server that enables Claude to collaborate with Google's Gemini AI models, providing tools for question answering, code review, brainstorming, test generation, and explanations.
                    Last updated -
                    MIT License
                  • -
                    security
                    F
                    license
                    -
                    quality
                    A server that allows interaction with Google's Gemini AI through the Gemini CLI tool using the Model Context Protocol, providing a standardized interface for querying Gemini with various options and configurations.
                    Last updated -
                  • -
                    security
                    F
                    license
                    -
                    quality
                    A Model Context Protocol server that connects to Google AI Studio/Gemini API, enabling content generation with support for various file types, conversation history, and system prompts.
                    Last updated -
                    1
                    39
                    17

                  View all related MCP servers

                  MCP directory API

                  We provide all the information about MCP servers via our MCP API.

                  curl -X GET 'https://glama.ai/api/mcp/v1/servers/orzcls/gemini-mcp-tool-windows-fixed'

                  If you have feedback or need assistance with the MCP directory API, please join our Discord server