AI Studio

Provides an MCP server that interfaces with Google AI Studio Gemini, enabling file-aware content generation and session-aware interactions.

javascript

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "eternnoir-aistudio-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "aistudio-mcp-server"
      ],
      "env": {
        "GEMINI_MODEL": "gemini-2.5-flash",
        "GEMINI_API_KEY": "your_api_key_here",
        "GEMINI_TIMEOUT": "600000",
        "GEMINI_MAX_FILES": "10",
        "GEMINI_TEMPERATURE": "0.2",
        "GEMINI_MAX_OUTPUT_TOKENS": "16384",
        "GEMINI_MAX_TOTAL_FILE_SIZE": "50"
      }
    }
  }
}

You run a dedicated MCP server that connects Google AI Studio / Gemini API to generate content using your files, history, and system prompts. It lets you perform tasks like image analysis, PDF processing, or audio transcription with configurable models and behavior, all through a lightweight MCP interface.

How to use

To use the AI Studio MCP Server, start the server locally or via an MCP client, then connect your client to it using the provided MCP configuration. You can run with an inline API key or a separate environment, and you can customize the Gemini model, timeouts, max output, and token/file limits to fit your workload. The server exposes a generate_content capability that accepts a user prompt, optional system prompt, and an optional set of files to influence the generation. When you couple prompts with files like images, PDFs, or documents, the model can produce richer, more contextual responses.

How to install

Prerequisites: Node.js 20.0.0 or higher and a Google AI Studio API key.

Using npx (recommended):

GEMINI_API_KEY=your_api_key npx -y aistudio-mcp-server

Additional setup notes

If you install locally, you can run the server with a Gemini API key set in your environment.

Local installation start example (after installation):

npm install -g aistudio-mcp-server
GEMINI_API_KEY=your_api_key aistudio-mcp-server

Available tools

generate_content

Generates content using Gemini with support for files, conversation history, and system prompts. It accepts a user prompt, an optional system prompt, and optional files, and returns a generated output.

Built by

VeilStrat

AI signals for GTM teams