How to Use the NVIDIA Vision MCP in Mastra AI

Build complex, multi-step vision workflows in Mastra AI using the NVIDIA Vision MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA Vision MCP to Mastra AI

Create your Vinkius account to connect NVIDIA Vision to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup NVIDIA Vision with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Complex vision workflows in Mastra AI

Chain `detect_objects` and `visual_grounding` within your agent workflows to automate decision making. If an object is found, the agent triggers the next step in your logic flow. This approach lets you handle failures with retries. You define the path, and the agent executes the sequence reliably.

Conditional vision tasks with Mastra AI

Create branches that depend on visual input using `image_segmentation` results. Your agent evaluates the segments and chooses the correct path for your specific business logic. This eliminates hard-coded rules. The system reacts to the actual image content in real time.

Production-ready vision MCP Server

Use the server to handle high-volume image processing requests within your Mastra AI pipelines. It provides raw access to `list_vision_models` so you can swap models based on current performance requirements. It keeps your infrastructure clean. You manage everything through the standard agent configuration.

Setup guide

Set up NVIDIA Vision MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All NVIDIA Vision tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "nvidia-vision-mcp-client",
  servers: {
    "nvidia-vision-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "NVIDIA Vision Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to NVIDIA Vision tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent NVIDIA Vision transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by NVIDIA. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect NVIDIA Vision now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about NVIDIA Vision MCP in Mastra AI

Add the server URL to your agent configuration. Mastra AI will automatically register the available tools for your workflow engine to execute.

The framework supports exponential backoff for all tool calls. If a visual analysis request fails, the system attempts a retry based on your defined policy.

You can toggle tool approval settings within your agent definition. This forces the agent to pause until you confirm the visual analysis results.

Yes, the tool outputs serve as inputs for your workflow conditions. You can route tasks based on the specific objects detected in an image.

All document images are processed through a private, authenticated channel. Data is ephemeral, and we never store your input files on our servers after the task completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript