一个与 Google AI Studio / Gemini API 集成的模型上下文协议（MCP）服务器，提供内容生成功能，支持文件、对话历史和系统提示。

安装与使用

先决条件

• Node.js 20.0.0 或更高
• Google AI Studio API 密钥

使用 NPX（推荐）

本地安装

配置

将你的 Google AI Studio API 密钥设置为环境变量：

可选配置

• GEMINI_MODEL：拟用Gemini型号（默认：gemini-2.5闪光灯）
• GEMINI_TIMEOUT：请求超时（毫秒）（默认：300000 = 5分钟）
• GEMINI_MAX_OUTPUT_TOKENS：最大输出令牌数（默认：8192）
• GEMINI_MAX_FILES：每个请求的最大文件数（默认：10）
• GEMINI_MAX_TOTAL_FILE_SIZE：最大总文件大小（MB）（默认：50）
• GEMINI_TEMPERATURE：生成温度（0-2，默认：0.2）

示例：

可用工具

generate_content

使用Gemini生成内容，全面支持文件、对话历史和系统提示。支持多种文件类型，包括图片、PDF、Office文档和文本文件。

参数：

AI Studio MCP Server

A Model Context Protocol (MCP) server that integrates with Google AI Studio / Gemini API, providing content generation capabilities with support for files, conversation history, and system prompts.

Installation and Usage

Prerequisites

• Node.js 20.0.0 or higher
• Google AI Studio API key

Using npx (Recommended)

GEMINI_API_KEY=your_api_key npx -y aistudio-mcp-server

Local Installation

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

Configuration

Set your Google AI Studio API key as an environment variable:

export GEMINI_API_KEY=your_api_key_here

Optional Configuration

• GEMINI_MODEL: Gemini model to use (default: gemini-2.5-flash)
• GEMINI_TIMEOUT: Request timeout in milliseconds (default: 300000 = 5 minutes)
• GEMINI_MAX_OUTPUT_TOKENS: Maximum output tokens (default: 8192)
• GEMINI_MAX_FILES: Maximum number of files per request (default: 10)
• GEMINI_MAX_TOTAL_FILE_SIZE: Maximum total file size in MB (default: 50)
• GEMINI_TEMPERATURE: Temperature for generation (0-2, default: 0.2)

Example:

export GEMINI_API_KEY=your_api_key_here
export GEMINI_MODEL=gemini-2.5-flash
export GEMINI_TIMEOUT=600000  # 10 minutes
export GEMINI_MAX_OUTPUT_TOKENS=16384  # More output tokens
export GEMINI_MAX_FILES=5  # Limit to 5 files per request
export GEMINI_MAX_TOTAL_FILE_SIZE=100  # 100MB limit
export GEMINI_TEMPERATURE=0.7  # More creative responses

Available Tools

generate_content

Generates content using Gemini with comprehensive support for files, conversation history, and system prompts. Supports various file types including images, PDFs, Office documents, and text files.

Parameters:

• user_prompt (string, required): User prompt for generation
• system_prompt (string, optional): System prompt to guide AI behavior
• files (array, optional): Array of files to include in generation
  • Each file object must have either path or content
  • path (string): Path to file
  • content (string): Base64 encoded file content
  • type (string, optional): MIME type (auto-detected from file extension)
• model (string, optional): Gemini model to use (default: gemini-2.5-flash)
• temperature (number, optional): Temperature for generation (0-2, default: 0.2). Lower values produce more focused responses, higher values more creative ones

Supported file types (Gemini 2.5 models):

• Images: JPG, JPEG, PNG, GIF, WebP, SVG, BMP, TIFF
• Video: MP4, AVI, MOV, WEBM, FLV, MPG, WMV (up to 10 files per request)
• Audio: MP3, WAV, AIFF, AAC, OGG, FLAC (up to 15MB per file)
• Documents: PDF (treated as images, one page = one image)
• Text: TXT, MD, JSON, XML, CSV, HTML

File limitations:

• Maximum file size: 15MB per audio/video/document file
• Maximum total request size: 20MB (2GB when using Cloud Storage)
• Video files: Up to 10 per request