Gemini Image Analysis

Analyzes image and video content from URLs or local files using the Gemini 2.0 Flash model.

An MCP server that receives image/video URLs or local file paths and analyzes their content using the Gemini 2.0 Flash model.(forked from github.com/champierre/image-mcp-server)

To install Image Analysis Server for Claude Desktop automatically viaSmithery:

npx -y @smithery/cli install @Rentapad/image-mcp-server --client claude

# Clone the repository git clone https://github.com/Rentapad/image-mcp-server-gemini.git cd image-mcp-server-gemini # Install dependencies npm install # Compile TypeScript npm run build

{ "mcpServers": { "image-video-analysis": { // Consider renaming for clarity "command": "node", "args": ["/path/to/image-mcp-server/dist/index.js"], "env": { "GEMINI_API_KEY": "your_gemini_api_key" } } } }

Add the following toclaude_desktop_config.json:

{ "mcpServers": { "image-video-analysis": { // Consider renaming for clarity "command": "node", "args": ["/path/to/image-mcp-server/dist/index.js"], "env": { "GEMINI_API_KEY": "your_gemini_api_key" } } } }

Once the MCP server is configured, the following tools become available:

- analyze_image: Receives one or more image URLs and analyzes their content.

- Arguments:imageUrls(array of strings, required),prompt(string, optional).

- Arguments:imagePaths(array of strings, required),prompt(string, optional).

- Arguments:videoUrls(array of strings, required),prompt(string, optional).

- Arguments:videoPaths(array of strings, required),prompt(string, optional).

- Arguments:youtubeUrl(string, required),prompt(string, optional).

Please analyze this image: https://example.com/image.jpg

Analyzing multiple images from local paths and comparing them:

Analyze these images: /path/to/your/image1.png, /path/to/your/image2.jpeg. Which one contains a cat?

(The client would callanalyze_image_from_pathwithimagePaths: ["/path/to/your/image1.png", "/path/to/your/image2.jpeg"]andprompt: "Which one contains a cat?")

Analyzing a video from URL with a specific prompt:

Summarize the content of this video: https://example.com/video.mp4

(The client would callanalyze_videowithvideoUrls: ["https://example.com/video.mp4"]andprompt: "Summarize the content of this video")

What is the main topic of this YouTube video? https://www.youtube.com/watch?v=dQw4w9WgXcQ

(The client would callanalyze_youtube_videowithyoutubeUrl: "https://www.youtube.com/watch?v=dQw4w9WgXcQ"andprompt: "What is the main topic of this YouTube video?")

- Size Limit:For videos provided via URL (analyze_video) or path (analyze_video_from_path), Gemini currently has limitations on the size of video data that can be processed directly (typically around 20MB after Base64 encoding). Larger videos may fail. YouTube analysis does not have this same client-side download limit.
- Supported MIME Types:The server attempts to map and use MIME types supported by Gemini for video. Officially supported types include:video/mp4,video/mpeg,video/mov,video/avi,video/x-flv,video/mpg,video/webm,video/wmv,video/3gpp. Files with other MIME types might be skipped. YouTube videos are handled separately.

When using the..._from_pathtools, the AI assistant (client) must specifyvalid file paths in the environment where this server is running.

- If the server is running on WSL:

- If the AI assistant has a Windows path (e.g.,C:\...), it needs to convert it to a WSL path (e.g.,/mnt/c/...) before passing it to the tool.
- If the AI assistant has a WSL path, it can pass it as is.

- If the AI assistant has a WSL path (e.g.,/home/user/...), it needs to convert it to a UNC path (e.g.,\\wsl$\Distro\...) before passing it to the tool.
- If the AI assistant has a Windows path, it can pass it as is.

Path conversion is the responsibility of the AI assistant (or its execution environment).The server will try to interpret the received path as is, applying basic security checks.

When runningnpm run build, you may see an error (TS7016) about missing TypeScript type definitions for themime-typesmodule.

src/index.ts:16:23 - error TS7016: Could not find a declaration file for module 'mime-types'. ...

This is a type checking error, and since the JavaScript compilation itself succeeds, itdoes not affect the server's execution. If you want to resolve this error, install the type definition file as a development dependency.

npm install --save-dev @types/mime-types # or yarn add --dev @types/mime-types

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.

Generate videos from images and manage tasks using the Vidu video generation API.

Server for advanced AI-driven video editing, semantic search, multilingual transcription, generative media, voice cloning, and content moderation.

All-in-one AI creative studio — generate videos, images, audio in 11 Indian languages, and 3D models via MCP. Hosted at mcp.arcframe.ai.

AVCLabs MCP integrates AI-powered video upscaling, quality enhancement, and SAM3 image segmentation into MCP workflows. It enhances low-resolution videos, cleans noisy footage, and extracts target objects through text prompts.

Official Cannon Studio MCP for AI video, image, 3D, audio, workflow, pricing, model, and developer API guidance.

Hosted remote MCP server for AI image and video generation from one Streamable HTTP endpoint.

A server for creating fast and free lipsync videos for digital avatars, supporting both realistic and cartoon styles.

Generates AI images and videos using the GPT4O Image Generator API.

MCP server for Grok video generation — text-to-video, image-to-video, and video editing