How to Use the Meshy (3D AI) MCP in Vercel AI SDK

Q: How do I handle long-running Meshy (3D AI) generation tasks inside my Vercel AI SDK app?

Start the process with createtextto3dpreview and get the task ID immediately. Use gettextto3dtask to poll the status from your Edge Function, streaming progress updates directly to your React components.

Q: Can I show the user their remaining credits using Meshy (3D AI) and Vercel AI SDK?

Yes. Call getbalance within your SDK tool configuration to fetch the current credit count. You can render this number in a sticky header so users know exactly how many generations they have left.

Q: What is the fastest way to clean up Meshy (3D AI) meshes in Vercel AI SDK?

Trigger createremesh directly from a button click in your UI. The SDK sends the target mesh to the MCP Server, which returns a cleaner topology that loads faster in WebGL.

Q: How do I handle 3D printing checks in my web application?

Run analyzeprintability on the generated mesh through the MCP Server. If it fails, call repairprintability to fix manifold issues before offering the STL download link to your user.

Pipe raw 3D assets straight into your Next.js frontend with Vercel AI SDK and Meshy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Meshy (3D AI) MCP to Vercel AI SDK

Create your Vinkius account to connect Meshy (3D AI) to Vercel AI SDK 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 Meshy (3D AI) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live text-to-3D streaming in Next.js

`create_text_to_3d_preview` kicks off the draft generation process, letting your users see low-poly shapes form in their browser window. You feed the output directly into your React state, bypassing the usual back-and-forth of polling endpoints manually. Once they approve the rough draft, trigger `create_text_to_3d_refine` to bake in high-resolution details. Because this MCP Server runs on Vercel's edge network, your UI updates the model's progress dynamically without blocking the main thread.

Image-to-3D MCP Server pipelines

`create_multi_image_to_3d` builds solid 3D models from several flat 2D source pictures uploaded by your users. The Vercel AI SDK handles the file references, passing them to the MCP Server to construct clean geometry from multiple perspectives. You display the resulting mesh immediately in a Three.js canvas using the SDK's real-time stream. If the balance runs low, the client checks `get_balance` before starting the render, keeping your API costs completely predictable.

Retexturing and rigging on the edge

`create_retexture` applies fresh paint to existing meshes based on text descriptions your users type directly into your chat interface. The Vercel AI SDK streams the text prompt to Meshy, then updates the material map on the fly. For character models, run `create_rigging` to automatically assign bones and weights right inside the user's browser session. Your frontend receives the rigged FBX file link directly through the SDK's tool output stream.

Setup guide

Set up Meshy (3D AI) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Meshy (3D AI) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Meshy (3D AI) transactions",
});

console.log(text);
await mcpClient.close();

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 Meshy. 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 Meshy (3D AI) 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 Meshy (3D AI) MCP in Vercel AI SDK

Start the process with `create_text_to_3d_preview` and get the task ID immediately. Use `get_text_to_3d_task` to poll the status from your Edge Function, streaming progress updates directly to your React components.

Yes. Call `get_balance` within your SDK tool configuration to fetch the current credit count. You can render this number in a sticky header so users know exactly how many generations they have left.

Trigger `create_remesh` directly from a button click in your UI. The SDK sends the target mesh to the MCP Server, which returns a cleaner topology that loads faster in WebGL.

Run `analyze_printability` on the generated mesh through the MCP Server. If it fails, call `repair_printability` to fix manifold issues before offering the STL download link to your user.

Your source images and generated OBJ files pass through secure, ephemeral V8 isolates. No assets are stored on Vinkius servers, keeping your proprietary game models completely isolated from other users.

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