Skip to content
Back to search

gemini-mcp-tool

MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/jamubc/gemini-mcp-tool with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/jamubc/gemini-mcp-tool'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jamubc--gemini-mcp-tool/badge.svg)](/listings/jamubc--gemini-mcp-tool)

HTML

<a href="/listings/jamubc--gemini-mcp-tool"><img src="/api/listings/jamubc--gemini-mcp-tool/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

claude mcp add gemini-cli -- npx -y gemini-mcp-tool

<details> <summary>For Windows users</summary>

Use `-- y` instead of `-y`:

claude mcp add gemini-cli -- npx -- y gemini-mcp-tool

</details>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 210 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Gemini MCP Tool
  2. <div align="center">
  3. [![GitHub Release](https://img.shields.io/github/v/release/jamubc/gemini-mcp-tool?logo=github&label=GitHub)](https://github.com/jamubc/gemini-mcp-tool/releases)
  4. [![npm version](https://img.shields.io/npm/v/gemini-mcp-tool)](https://www.npmjs.com/package/gemini-mcp-tool)
  5. [![npm downloads](https://img.shields.io/npm/dt/gemini-mcp-tool)](https://www.npmjs.com/package/gemini-mcp-tool)
  6. [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
  7. [![Open Source](https://img.shields.io/badge/Open%20Source-❤️-red.svg)](https://github.com/jamubc/gemini-mcp-tool)
  8. </div>
  9. > 📚 **[View Full Documentation](https://jamubc.github.io/gemini-mcp-tool/)** - Search me!, Examples, FAQ, Troubleshooting, Best Practices
  10. This is a simple Model Context Protocol (MCP) server that allows AI assistants to interact with the [Gemini CLI](https://github.com/google-gemini/gemini-cli). It enables the AI to leverage the power of Gemini's massive token window for large analysis, especially with large files and codebases using the `@` syntax for direction.
  11. - Ask gemini natural questions, through claude or Brainstorm new ideas in a party of 3!
  12. <a href="https://glama.ai/mcp/servers/@jamubc/gemini-mcp-tool">
  13. <img width="380" height="200" src="https://glama.ai/mcp/servers/@jamubc/gemini-mcp-tool/badge" alt="Gemini Tool MCP server" />
  14. </a>
  15. ## TLDR: [![Claude](https://img.shields.io/badge/Claude-D97757?logo=claude&logoColor=fff)](#) + [![Gemini](https://img.shields.io/badge/Google%20Gemini-886FBF?logo=googlegemini&logoColor=fff)](#)([![Google Antigravity CLI](https://img.shields.io/badge/Antigravity%20%28agy%29-4285F4?logo=google&logoColor=fff)](#))
  16. **Goal**: Use Gemini's powerful analysis capabilities directly in Claude Code to save tokens and analyze large files.
  17. ## Prerequisites
  18. <details>
  19. <summary>🚀 <strong>Important: Gemini CLI is retired. This tool now defaults to Antigravity CLI (`agy`)</strong></summary>
  20. On **2026-06-18**, Google retired the Gemini CLI for **free, Google AI Pro, and Google AI Ultra** users (and individual Gemini Code Assist / GitHub-org users). Its successor is the **Antigravity CLI** (`agy`). See [Google's announcement](https://goo.gle/gemini-cli-migration).
  21. **From 2026-06-18 this tool selects the `agy` backend automatically.** If you are on an affected tier, just install `agy`:
  22. ```bash
  23. curl -fsSL https://antigravity.google/cli/install.sh | bash # macOS / Linux
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 37 on GitHub
  24. ```
  25. Then run `agy` once to sign in. Nothing else to change.
  26. **Enterprise / Standard-license or paid-API-key user?** Your Gemini CLI access is **unaffected** by the retirement. To keep using it, set one env var on the MCP server:
  27. ```bash
  28. GEMINI_MCP_BACKEND=gemini
  29. ```
  30. | Variable | Purpose |
  31. | --- | --- |
  32. | `GEMINI_MCP_BACKEND` | `gemini` or `agy`/`antigravity`. Unset uses the date-aware default (`agy` from 2026-06-18). |
  33. | `AGY_CLI_PATH` | Full path to the `agy` binary if it isn't on the server's PATH. |
  34. | `GEMINI_MCP_TIMEOUT` | Overall CLI run timeout in minutes (default 45). |
  35. The `agy` backend is **experimental**: print mode is Gemini 3.5 Flash-only, replies come from `agy`'s stdout (transcript recovery only as a fallback), and tool execution isn't sandboxed in `-p`. The tool emits a notice when a requested `model`/`sandbox` can't be honored, and surfaces `agy`'s own errors (quota, auth) verbatim. Full analysis: [docs/migration/antigravity-cli.md](docs/migration/antigravity-cli.md).
  36. </details>
  37. Before using this tool, ensure you have:
  38. 1. **[Node.js](https://nodejs.org/)** (v16.0.0 or higher)
  39. 2. **[Google Gemini CLI](https://github.com/google-gemini/gemini-cli)** installed and configured
  40. ### One-Line Setup
  41. ```bash
  42. claude mcp add gemini-cli -- npx -y gemini-mcp-tool
  43. ```
  44. <details>
  45. <summary>For Windows users</summary>
  46. Use `-- y` instead of `-y`:
  47. ```bash
  48. claude mcp add gemini-cli -- npx -- y gemini-mcp-tool
  49. ```
  50. </details>
  51. ### Verify Installation
  52. Type `/mcp` inside Claude Code to verify the gemini-cli MCP is active.
  53. ---
  54. ### Alternative: Import from Claude Desktop
  55. If you already have it configured in Claude Desktop:
  56. 1. Add to your Claude Desktop config:
  57. ```json
  58. "gemini-cli": {
  59. "command": "npx",
  60. "args": ["-y", "gemini-mcp-tool"]
  61. }
  62. ```
  63. 2. Import to Claude Code:
  64. ```bash
  65. claude mcp add-from-claude-desktop
  66. ```
  67. ## Configuration
  68. Register the MCP server with your MCP client:
  69. ### For NPX Usage (Recommended)
  70. Add this configuration to your Claude Desktop config file:
  71. ```json
  72. {
  73. "mcpServers": {
  74. "gemini-cli": {
  75. "command": "npx",
  76. "args": ["-y", "gemini-mcp-tool"]
  77. }
  78. }
  79. }
  80. ```
  81. ### For Global Installation
  82. If you installed globally, use this configuration instead:
  83. ```json
  84. {
  85. "mcpServers": {
  86. "gemini-cli": {
  87. "command": "gemini-mcp"
  88. }
  89. }
  90. }
  91. ```
  92. **Configuration File Locations:**
  93. - **Claude Desktop**:
  94. - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
  95. - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
  96. - **Linux**: `~/.config/claude/claude_desktop_config.json`
  97. After updating the configuration, restart your terminal session.
  98. ## Example Workflow
  99. - **Natural language**: "use gemini to explain index.html", "understand the massive project using gemini", "ask gemini to search for latest news"
  100. - **Claude Code**: Type `/gemini-cli` and commands will populate in Claude Code's interface.
  101. ## Usage Examples
  102. ### With File References (using @ syntax)
  103. - `ask gemini to analyze @src/main.js and explain what it does`
  104. - `use gemini to summarize @. the current directory`
  105. - `analyze @package.json and tell me about dependencies`
  106. ### General Questions (without files)
  107. - `ask gemini to search for the latest tech news`
  108. - `use gemini to explain div centering`
  109. - `ask gemini about best practices for React development related to @file_im_confused_about`
  110. ### Using Gemini CLI's Sandbox Mode (-s)
  111. The sandbox mode allows you to safely test code changes, run scripts, or execute potentially risky operations in an isolated environment.
  112. - `use gemini sandbox to create and run a Python script that processes data`
  113. - `ask gemini to safely test @script.py and explain what it does`
  114. - `use gemini sandbox to install numpy and create a data visualization`
  115. - `test this code safely: Create a script that makes HTTP requests to an API`
  116. ### Tools (for the AI)
  117. These tools are designed to be used by the AI assistant.
  118. - **`ask-gemini`**: Asks Google Gemini for its perspective. Can be used for general questions or complex analysis of files.
  119. - **`prompt`** (required): The analysis request. Use the `@` syntax to include file or directory references (e.g., `@src/main.js explain this code`) or ask general questions (e.g., `Please use a web search to find the latest news stories`).
  120. - **`model`** (optional): The Gemini model to use. Defaults to `gemini-2.5-pro`.
  121. - **`sandbox`** (optional): Set to `true` to run in sandbox mode for safe code execution.
  122. - **`sandbox-test`**: Safely executes code or commands in Gemini's sandbox environment. Always runs in sandbox mode.
  123. - **`prompt`** (required): Code testing request (e.g., `Create and run a Python script that...` or `@script.py Run this safely`).
  124. - **`model`** (optional): The Gemini model to use.
  125. - **`Ping`**: A simple test tool that echoes back a message.
  126. - **`Help`**: Shows the Gemini CLI help text.
  127. ### Slash Commands (for the User)
  128. You can use these commands directly in Claude Code's interface (compatibility with other clients has not been tested).
  129. - **/analyze**: Analyzes files or directories using Gemini, or asks general questions.
  130. - **`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`).
  131. - **/sandbox**: Safely tests code or scripts in Gemini's sandbox environment.
  132. - **`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`).
  133. - **/help**: Displays the Gemini CLI help information.
  134. - **/ping**: Tests the connection to the server.
  135. - **`message`** (optional): A message to echo back.
  136. ## Contributing
  137. Contributions are welcome! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details on how to submit pull requests, report issues, and contribute to the project.
  138. ## License
  139. This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
  140. **Disclaimer:** This is an unofficial, third-party tool and is not affiliated with, endorsed, or sponsored by Google.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.