claude_code-gemini
Simplified Gemini for Claude Code.
claude mcp add --transport stdio raiansar-claude_code-gemini-mcp python ~/.claude-mcp-servers/gemini-collab/server.py \ --env GOOGLE_GEMINI_API_KEY="your-google-gemini-api-key"
How to use
This MCP server bridges Claude Code with Google's Gemini AI, enabling seamless collaboration between code editing and Gemini's capabilities. You can ask Gemini questions directly, request code reviews focused on security or performance, and brainstorm ideas for features or architectures. The available tools include: ask_gemini to query Gemini about general topics or explanations, gemini_code_review to get code reviews with a focus area you specify, and gemini_brainstorm to brainstorm solutions or architectures. To use, start Claude Code and invoke the corresponding MCP tools via the Claude Code command palette or the provided mcp commands (e.g., mcp__gemini-collab__ask_gemini, mcp__gemini-collab__gemini_code_review, mcp__gemini-collab__gemini_brainstorm). The server handles authentication with Google Gemini through your API key and provides a lightweight bridge so Claude Code can leverage Gemini inside your coding workflow.
How to install
Prerequisites:\n- Python 3.8+ installed\n- Claude Code CLI installed\n- Google Gemini API key (Get one free)\n\nOption A: One-Line Install\nbash\ncurl -sSL https://raw.githubusercontent.com/RaiAnsar/claude_code-gemini-mcp/main/install.sh | bash\n````\nOption B: Manual Install\n1. Clone this repo:\nbash\ngit clone https://github.com/RaiAnsar/claude_code-gemini-mcp.git\ncd claude_code-gemini-mcp\n\n2. Run setup with your API key:\nbash\n./setup.sh YOUR_GEMINI_API_KEY\n```\nThis will install the MCP server globally for Claude Code to discover. After setup, the server will be available under the gemini-collab identifier.
Additional notes
Tips and notes:\n- Ensure your Google Gemini API key is valid and has access enabled.\n- The MCP server stores its files under the installation path, e.g., ~/.claude-mcp-servers/gemini-collab/. If you move or modify files, update the server path accordingly.\n- If the MCP doesn't show up in Claude Code, try listing or reinstalling with the CLI: claude mcp list, claude mcp remove gemini-collab, claude mcp add --scope user gemini-collab python3 ~/.claude-mcp-servers/gemini-collab/server.py.\n- You may need to install the Google Generative AI Python SDK: pip install google-generativeai.\n- The environment variable GOOGLE_GEMINI_API_KEY should be kept secure and not committed to public repositories.
Related MCP Servers
sympy
A MCP server for symbolic manipulation of mathematical expressions
mcp_server_filesystem
MCP File System Server: A secure Model Context Protocol server that provides file operations for AI assistants. Enables Claude and other assistants to safely read, write, and list files in a designated project directory with robust path validation and security controls.
kaggle
Kaggle-MCP: Connect Claude AI to the Kaggle API through the Model Context Protocol (MCP), enabling competition, dataset, and kernel operations through the AI interface.
claude_autoapprove_mcp
An MCP server to inject auto-approve MCP functionality into Claude Desktop
aiNOC
Networking project for AI-based troubleshooting of CCNP Enterprise topics in a multi-vendor, multi-protocol, multi-area/multi-AS, OSI L3-focused topology using Claude Code, FastMCP, Python, Scrapli, REST, Containerlab, Jira, etc.
microsoft
A Microsoft Graph API integration MCP server that provides AI assistants with comprehensive access to Microsoft 365 services through the Model Context Protocol (MCP). It enables natural language automation of email, calendar, file management, and contact operations across multiple Microsoft accounts.
