Genai MCP Server

[![NPM Downloads](https://img.shields.io/npm/dw/%40google%2Fgenai)](https://www.npmjs.com/package/@google/genai) [![Node

Remote serverstreamable-httpTypeScript

What is the Genai MCP server?

Connect Genai to Claude, Cursor or any other MCP client and it stops being a tab you switch to. . The genai mcp server is what makes that connection.

What the server does

The Google Gen AI SDK is designed to work with Gemini 2.0+ features.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Browser — The Browser tool exposed by this server
  • Streaming — For quicker, more responsive API interactions use the generateContentStream method which yields chunks as they're generated:
  • Content — The Content tool exposed by this server
  • Part — Parts will be aggregated on a singular Content, with role 'user'

Credentials and setup notes

Configuration is passed through the environment: GOOGLE_API_KEY, GOOGLE_GENAI_USE_ENTERPRISE, GOOGLE_CLOUD_PROJECT, GOOGLE_CLOUD_LOCATION, GEMINI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  1. Node.js version 20 or later

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Genai's toolset — Browser, Streaming, Content and 1 more — is a fair guide to whether it matches your workflow. It is maintained by google-wombot; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
BrowserThe Browser tool exposed by this server.
StreamingFor quicker, more responsive API interactions use the generateContentStream method which yields chunks as they're generated:
ContentThe Content tool exposed by this server.
PartParts will be aggregated on a singular Content, with role 'user'.

How to install the Genai MCP server

{
  "mcpServers": {
    "genai": {
      "command": "npx",
      "args": ["-y", "@google/genai"],
      "env": {
        "GOOGLE_API_KEY": "your-value",
        "GOOGLE_GENAI_USE_ENTERPRISE": "your-value",
        "GOOGLE_CLOUD_PROJECT": "your-value",
        "GOOGLE_CLOUD_LOCATION": "your-value",
        "GEMINI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  1. Node.js version 20 or later
VariableDescriptionRequired
GOOGLE_API_KEYCredential the server authenticates with.Yes
GOOGLE_GENAI_USE_ENTERPRISEConfiguration value read at startup.Optional
GOOGLE_CLOUD_PROJECTConfiguration value read at startup.Optional
GOOGLE_CLOUD_LOCATIONConfiguration value read at startup.Optional
GEMINI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Genai to Browser.
  • Use Genai to Streaming.
  • Use Genai to Content.

Frequently asked questions

It connects Genai to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Browser, Streaming, Content, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Genai directly.