# Gemini Pro MCP

Gemini Pro MCP — an MCP server for Claude Code and Codex that bridges your Google AI Pro subscription and up to thirty-six Gemini tools.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12 repo stars
- Author: Muzaqil555
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Muzaqil555/gemini-pro-mcp
- Updated: 2026-11-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/gemini-pro-mcp

## What it does

This MCP server brings your Google AI Pro subscription limits directly into coding agents without pay-per-token API charges. The toolset covers Deep Research, Flow video generation, Gemini Notebooks audio overviews, and the Jules agent through the Antigravity CLI. Setup requires `uv` or Python 3.10 or newer, an AI Pro account, and the Antigravity CLI.

The `setup` command configures supported clients automatically, while `doctor` inspects the environment and status. Browser automation and paid media calls remain disabled by default until explicitly enabled via environment variables.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `GEMINI_API_KEY`, `JULES_API_KEY`, `GEMINI_PRO_ENABLE_FLOW`, `GEMINI_PRO_ENABLE_BROWSER` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env GEMINI_API_KEY=<GEMINI_API_KEY> --env JULES_API_KEY=<JULES_API_KEY> --env GEMINI_PRO_ENABLE_FLOW=<GEMINI_PRO_ENABLE_FLOW> --env GEMINI_PRO_ENABLE_BROWSER=<GEMINI_PRO_ENABLE_BROWSER> --transport stdio gemini-pro-mcp -- uvx gemini-pro-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from gemini-pro-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add gemini-pro-mcp --env GEMINI_API_KEY=<GEMINI_API_KEY> --env JULES_API_KEY=<JULES_API_KEY> --env GEMINI_PRO_ENABLE_FLOW=<GEMINI_PRO_ENABLE_FLOW> --env GEMINI_PRO_ENABLE_BROWSER=<GEMINI_PRO_ENABLE_BROWSER> -- uvx gemini-pro-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from gemini-pro-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "gemini-pro-mcp": {
            "command": "uvx",
            "args": [
                "gemini-pro-mcp"
            ],
            "env": {
                "GEMINI_API_KEY": "<GEMINI_API_KEY>",
                "JULES_API_KEY": "<JULES_API_KEY>",
                "GEMINI_PRO_ENABLE_FLOW": "<GEMINI_PRO_ENABLE_FLOW>",
                "GEMINI_PRO_ENABLE_BROWSER": "<GEMINI_PRO_ENABLE_BROWSER>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from gemini-pro-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "gemini-pro-mcp": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gemini-pro-mcp"
            ],
            "env": {
                "GEMINI_API_KEY": "<GEMINI_API_KEY>",
                "JULES_API_KEY": "<JULES_API_KEY>",
                "GEMINI_PRO_ENABLE_FLOW": "<GEMINI_PRO_ENABLE_FLOW>",
                "GEMINI_PRO_ENABLE_BROWSER": "<GEMINI_PRO_ENABLE_BROWSER>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from gemini-pro-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e GEMINI_API_KEY=<GEMINI_API_KEY> -e JULES_API_KEY=<JULES_API_KEY> -e GEMINI_PRO_ENABLE_FLOW=<GEMINI_PRO_ENABLE_FLOW> -e GEMINI_PRO_ENABLE_BROWSER=<GEMINI_PRO_ENABLE_BROWSER> gemini-pro-mcp uvx gemini-pro-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from gemini-pro-mcp <command>

## When to use it
- get a code review from Gemini on local files
- run a deep research query with sources
- generate videos using Flow credits
- turn PDF documents into notebook audio overviews

## Example prompts
- Get a second opinion from Gemini on `src/auth.py`.
- Research what changed in Flutter 3.47, with sources.

## Similar
- [gemini-agents-api](https://affpapa.org/en/nevibecode/skills/gemini-agents-api.md) — skill · 9466 installs
- [gemini-api](https://affpapa.org/en/nevibecode/skills/gemini-api.md) — skill · 17116 installs
- [google-gemini-omni-video](https://affpapa.org/en/nevibecode/skills/google-gemini-omni-video.md) — skill · 144 installs
- [gemini-live-audio](https://affpapa.org/en/nevibecode/skills/gemini-live-audio.md) — skill · 137 installs
- [gemini-api-dev](https://affpapa.org/en/nevibecode/skills/gemini-api-dev.md) — skill · 27800 installs
- [gemini-computer-use](https://affpapa.org/en/nevibecode/skills/gemini-computer-use.md) — skill · 1200 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
