VisionCraft
VisionCraft MCP delivers up-to-date, specialized computer vision and Gen-AI knowledge directly to Claude and other AI assistants.
What is VisionCraft?
VisionCraft is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to visioncraft mcp delivers up-to-date, specialized computer vision and gen-ai knowledge directly to claude and other ai assistants.
VisionCraft MCP delivers up-to-date, specialized computer vision and Gen-AI knowledge directly to Claude and other AI assistants.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- VisionCraft MCP delivers up-to-date, specialized computer vi
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx visioncraft-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use VisionCraft
VisionCraft MCP Server connects Claude and other AI assistants to a curated knowledge base of over 100,000 computer vision and generative AI repositories, indexed by the proprietary Raven engine. It exposes a single `vision-query` tool that lets models search for up-to-date implementations, techniques, and code examples across topics like object detection, image segmentation, 3D vision, and vision-language models. Developers working on CV and GenAI projects use it to pull accurate, current library documentation and code snippets without leaving their AI assistant.
Prerequisites
- Node.js 18.0.0 or later
- A free VisionCraft API key (sign up at visioncraft-app.augmentedstartups.com)
- An MCP-compatible client such as Claude Desktop, Cursor, Windsurf, or VS Code with the Cline extension
Obtain a free API key
Navigate to visioncraft-app.augmentedstartups.com and create a free account. After signing up, copy your API key from the dashboard — you will need it in the next step.
Add VisionCraft to your MCP client configuration
Open your MCP client config file (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json for Claude Desktop) and add the VisionCraft server entry, replacing YOUR_API_KEY_HERE with the key you copied.
{
"mcpServers": {
"visioncraft": {
"command": "npx",
"args": ["-y", "visioncraft-mcp@latest", "--api-key", "YOUR_API_KEY_HERE"]
}
}
}Restart your MCP client
Quit and relaunch Claude Desktop (or reload your editor). The VisionCraft server will start automatically on the next launch and the vision-query tool will appear in the tool list.
Include the activation phrase in your prompts
Add 'use visioncraft mcp' to your prompt so the assistant routes the query through the VisionCraft knowledge base rather than relying on its training data.
VisionCraft Examples
Client configuration
Claude Desktop config for VisionCraft MCP Server with an API key passed as a CLI argument.
{
"mcpServers": {
"visioncraft": {
"command": "npx",
"args": ["-y", "visioncraft-mcp@latest", "--api-key", "YOUR_API_KEY_HERE"]
}
}
}Prompts to try
Example prompts that route through the VisionCraft knowledge base.
- "Give me the code for real-time object detection with YOLOv9. Use visioncraft mcp."
- "Show me a Python example using SAM 2 for video segmentation. Use visioncraft mcp."
- "What are the latest vision-language models and how do I use them with Hugging Face? Use visioncraft mcp."
- "Find a working implementation of DepthAnything v2 for monocular depth estimation. Use visioncraft mcp."
- "Give me code for the OpenAI Agents SDK. Use visioncraft mcp tool."Troubleshooting VisionCraft
vision-query tool returns 401 Unauthorized errors
Your API key is missing or incorrect. Double-check that the --api-key argument in your config matches the key shown in the VisionCraft dashboard. API keys are per-account and must not contain extra whitespace.
The visioncraft-mcp package fails to install because of Node.js version mismatch
VisionCraft requires Node.js 18.0.0 or higher. Run `node --version` to check your version and upgrade via nvm (`nvm install 20`) or the official Node.js installer if needed.
Claude ignores the VisionCraft tool and answers from training data
Explicitly include 'use visioncraft mcp' or 'use the visioncraft tool' in your prompt. Without this instruction the model may not route CV questions through the tool automatically.
Frequently Asked Questions about VisionCraft
What is VisionCraft?
VisionCraft is a Model Context Protocol (MCP) server that visioncraft mcp delivers up-to-date, specialized computer vision and gen-ai knowledge directly to claude and other ai assistants. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install VisionCraft?
Follow the installation instructions on the VisionCraft GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with VisionCraft?
VisionCraft works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is VisionCraft free to use?
Yes, VisionCraft is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
VisionCraft Alternatives — Similar Data Science & ML Servers
Looking for alternatives to VisionCraft? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up VisionCraft in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use VisionCraft?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.