An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Meshy 3d AI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn text prompts and images into textured 3D models.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 17 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 17 available through Meshy.

  1. 01

    Create image to image

    Starts an image to image task to transform visual styles.

  2. 02

    Create multi color print

    Triggers a task to prepare a model for multi-color printing.

  3. 03

    Create multi image to 3d

    Generates a 3D model using multiple reference images for better accuracy.

  4. 04

    Create text to image

    Creates a 2D image based on your text description.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 17 available through Meshy.

  1. 05

    Delete text to 3d task

    Removes a specific text to 3D generation task from your history.

  2. 06

    Create text to 3d refine

    Refines an existing text to 3D model to improve its quality.

  3. 07

    Create rigging

    Sets up a rigging task to prepare a mesh for animation.

  4. 08

    List text to 3d tasks

    Retrieves a list of your recent text to 3D generation tasks.

Capability set03 / 05

09-11

3 capabilities in this set.

Part of 17 available through Meshy.

  1. 09

    Get balance

    Checks your current Meshy account balance.

  2. 10

    Get text to 3d task

    Fetches the specific details and status of a single text to 3D task.

  3. 11

    Analyze printability

    Checks a 3D model to see if it is suitable for printing.

Capability set04 / 05

12-14

3 capabilities in this set.

Part of 17 available through Meshy.

  1. 12

    Create animation

    Starts a task to generate animations for your 3D models.

  2. 13

    Create image to 3d

    Converts a single reference image into a 3D mesh.

  3. 14

    Create remesh

    Adjusts the topology of a mesh through a remeshing task.

Capability set05 / 05

15-17

3 capabilities in this set.

Part of 17 available through Meshy.

  1. 15

    Create retexture

    Applies new textures to a model using text or image guidance.

  2. 16

    Create text to 3d preview

    Generates an initial 3D preview from a text prompt.

  3. 17

    Repair printability

    Attempts to fix issues in a model to make it printable.

Real work

What teams actually run

01

Rapid Prototyping

A developer describes a prop in text to get a 3D preview for a game level instantly.

02

Asset Iteration

An artist takes an existing model and uses retexturing to test different visual themes.

03

3D Printing Prep

A maker uses the printability capabilities to check and fix a model before sending it to a printer.

04

Concept Visualization

An agency turns a client's sketch into a 3D object to show spatial depth.

Automate a task

Put Meshy to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Meshy works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Meshy to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1084ms average. Fast in production.

Meshy is checked daily against the live service.

Daily averagePeak 1361ms
Oct 3Today
Fastest day
904ms
Slowest day
1361ms
14-day trend
Slowing+15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 17 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Meshy, so you can see the experience inside your AI.

It does not authenticate your account with Meshy. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Meshy Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_E4aVxpL4rnJ2I2mM5xkfSreAbJ39t8Njauv4tQ22/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Meshy capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "meshy-3d-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_E4aVxpL4rnJ2I2mM5xkfSreAbJ39t8Njauv4tQ22/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Meshy in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Meshy owners hand off.

This MCP is built for technical creatives who need to move from concept to 3D asset without leaving their coding or design environments.

  • 01

    Game Developers

    They use the agent to generate base meshes and textures for rapid prototyping.

  • 02

    3D Artists

    They hand off tedious tasks like initial block-outs and UV mapping to the AI.

  • 03

    Creative Agencies

    They use it to quickly visualize 3D concepts from sketches for client presentations.

FAQ

Questions Meshy owners ask.

  • 01

    How do I use Meshy with Claude?

    Once you connect the Meshy MCP through Vinkius, you can simply ask Claude to perform 3D tasks like creating a model from a text prompt.

  • 02

    Can I turn a photo into a 3D model?

    Yes, you can use the image to 3D capabilities to convert a single image or multiple reference images into a 3D mesh.

  • 03

    Do I need to provide my own API key?

    Yes, you will need to enter your Meshy API Key to authenticate the connection.

  • 04

    Can I optimize meshes for games?

    Yes, the MCP includes remeshing capabilities that allow you to adjust topology and target specific polycounts.

  • 05

    Is it possible to check if a model is printable?

    Yes, the MCP provides capabilities to analyze and repair models specifically for 3D printing.

  • 06

    How do I add high-quality textures to a 3D model I just generated from text?

    After creating a preview with create_text_to_3d_preview, use the create_text_to_3d_refine capability with the resulting task ID. You can enable PBR and HD textures to get professional results.

  • 07

    Can I use multiple photos of an object to create a better 3D model?

    Yes! Use the create_multi_image_to_3d capability and provide an array of up to 4 image URLs showing different angles of the object for much higher accuracy.

  • 08

    Is it possible to reduce the polygon count for game engine optimization?

    Absolutely. Use the create_remesh capability on any existing model ID. You can specify the target_polycount and choose between triangle or quad topology.

Explore

More in Design Creative

Suggestions

Connect Meshy to Claude, Cursor, ChatGPT & more