gemini-analyze-image

Analyze images in JPG, PNG, WebP, and other formats to extract summaries, objects, text, or detailed insights using Gemini's multimodal vision capabilities. Supports context-based enhancements for specific use cases.

Instructions

Analyze images using Gemini's multimodal vision capabilities (with learned user preferences)

Input Schema

Name	Required	Description
`analysis_type`	No	Type of analysis to perform: "summary", "objects", "text", "detailed", or "custom"
`context`	No	Optional context for intelligent enhancement (e.g., "medical", "architectural", "nature")
`file_path`	Yes	Path to the image file to analyze (supports JPEG, PNG, WebP, HEIC, HEIF, BMP, GIF)

Input Schema (JSON Schema)

{
  "properties": {
    "analysis_type": {
      "description": "Type of analysis to perform: \"summary\", \"objects\", \"text\", \"detailed\", or \"custom\"",
      "enum": [
        "summary",
        "objects",
        "text",
        "detailed",
        "custom"
      ],
      "type": "string"
    },
    "context": {
      "description": "Optional context for intelligent enhancement (e.g., \"medical\", \"architectural\", \"nature\")",
      "type": "string"
    },
    "file_path": {
      "description": "Path to the image file to analyze (supports JPEG, PNG, WebP, HEIC, HEIF, BMP, GIF)",
      "type": "string"
    }
  },
  "required": [
    "file_path"
  ],
  "type": "object"
}

Gemini MCP Server for Claude Desktop

gemini-analyze-image

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Gemini MCP Server for Claude Desktop

Related Tools

MCP directory API