NVIDIA Vision MCP Server for Windsurf 9 tools — connect in under 2 minutes
Windsurf brings agentic AI coding to a purpose-built IDE. Connect NVIDIA Vision through the Vinkius and Cascade will auto-discover every tool — ask questions, generate code, and act on live data without leaving your editor.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
Vinkius Desktop App
The modern way to manage MCP Servers — no config files, no terminal commands. Install NVIDIA Vision and 2,500+ MCP Servers from a single visual interface.
{
"mcpServers": {
"nvidia-vision": {
"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}
}
}
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About NVIDIA Vision MCP Server
Connect NVIDIA Vision to any AI agent and unlock powerful image understanding and generation — create images with Stable Diffusion, analyze visuals with Kosmos-2, answer questions about images, and perform object detection through natural conversation.
Windsurf's Cascade agent chains multiple NVIDIA Vision tool calls autonomously — query data, analyze results, and generate code in a single agentic session. Paste the Vinkius Edge URL, reload, and all 9 tools are immediately available. Real-time tool feedback appears inline, so you see API responses directly in your editor.
What you can do
- Generate Images — Create images from text prompts using Stable Diffusion models
- Visual Q&A — Ask questions about any image and get detailed answers
- Image Captioning — Generate detailed descriptions of image contents
- Object Detection — Identify and list all objects visible in an image
- Document Understanding — Extract information from scanned documents and forms
- Visual Grounding — Locate specific objects or phrases within images
- Style Transfer — Apply artistic styles to existing images
- Image Segmentation — Segment images into distinct object regions
The NVIDIA Vision MCP Server exposes 9 tools through the Vinkius. Connect it to Windsurf in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect NVIDIA Vision to Windsurf via MCP
Follow these steps to integrate the NVIDIA Vision MCP Server with Windsurf.
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Add the server
Paste the JSON configuration above into mcp_config.json
Save and reload
Windsurf will detect the new server automatically
Start using NVIDIA Vision
Open Cascade and ask: "Using NVIDIA Vision, help me..." — 9 tools available
Why Use Windsurf with the NVIDIA Vision MCP Server
Windsurf provides unique advantages when paired with NVIDIA Vision through the Model Context Protocol.
Windsurf's Cascade agent autonomously chains multiple tool calls in sequence, solving complex multi-step tasks without manual intervention
Purpose-built for agentic workflows — Cascade understands context across your entire codebase and integrates MCP tools natively
JSON-based configuration means zero code changes: paste a URL, reload, and all 9 tools are immediately available
Real-time tool feedback is displayed inline, so you see API responses directly in your editor without switching contexts
NVIDIA Vision + Windsurf Use Cases
Practical scenarios where Windsurf combined with the NVIDIA Vision MCP Server delivers measurable value.
Automated code generation: ask Cascade to fetch data from NVIDIA Vision and generate models, types, or handlers based on real API responses
Live debugging: query NVIDIA Vision tools mid-session to inspect production data while debugging without leaving the editor
Documentation generation: pull schema information from NVIDIA Vision and have Cascade generate comprehensive API docs automatically
Rapid prototyping: combine NVIDIA Vision data with Cascade's code generation to scaffold entire features in minutes
NVIDIA Vision MCP Tools for Windsurf (9)
These 9 tools become available when you connect NVIDIA Vision to Windsurf via MCP:
detect_objects
Detect and list all objects in an image
document_qa
Works with scanned documents, forms, receipts. Ask questions about a document image (OCR + understanding)
generate_image
Model options: "stabilityai/stable-diffusion-3-medium", "stabilityai/stable-diffusion-xl-base-1.0". Size format: "1024x1024". Generate an image from a text prompt using Stable Diffusion
image_captioning
Generate a detailed caption for an image
image_segmentation
Segment and identify all objects in an image
list_vision_models
List available vision models on NVIDIA API Catalog
style_transfer
Apply an artistic style to an image
visual_grounding
Locate a specific object or phrase in an image
visual_question_answering
Provide a public image URL. Ask a question about an image
Example Prompts for NVIDIA Vision in Windsurf
Ready-to-use prompts you can give your Windsurf agent to start working with NVIDIA Vision immediately.
"Generate an image of a futuristic city at sunset."
"What objects do you see in this image: https://example.com/photo.jpg"
"Describe this image in detail: https://example.com/document.png"
Troubleshooting NVIDIA Vision MCP Server with Windsurf
Common issues when connecting NVIDIA Vision to Windsurf through the Vinkius, and how to resolve them.
Server not connecting
NVIDIA Vision + Windsurf FAQ
Common questions about integrating NVIDIA Vision MCP Server with Windsurf.
How does Windsurf discover MCP tools?
mcp_config.json file on startup and connects to each configured server via Streamable HTTP. Tools are listed in the MCP panel and available to Cascade automatically.Can Cascade chain multiple MCP tool calls?
Does Windsurf support multiple MCP servers?
mcp_config.json. Each server's tools appear in the MCP panel and Cascade can use tools from different servers in a single flow.Connect NVIDIA Vision with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect NVIDIA Vision to Windsurf
Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.