Meshy MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Meshy MCP or direct API to generate 3D assets, render photorealistic images, animate motion sequences, and process and export optimized models through natural language.

Meshy logoMeshy
Api Key

Meshy is a Creative Lab providing generative 3D, image, motion, animation, and model-processing APIs. It lets teams quickly create, iterate, and export production-ready creative assets.

27 Tools

Try Meshy now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Meshy
Try asking
TOOLS

Supported Tools

Every Meshy action and event your agent gets out of the box.

Cancel Creative Lab Task

Request deletion of a Creative Lab task by type and ID.

Create Animation Task

Start a 3-credit task that applies either a selected library animation or a succeeded Text to Motion clip to a completed rigging task and return the animation task ID.

Create Auto Split Task

Split a succeeded untextured Meshy 6 or Meshy 7 model into separately printable parts and return the task ID.

Create Collapsible Fidget Task

Start an entitled 6-credit task that generates a collapsible fidget directly from an image and return the task ID.

Create Convert Task

Start a 1-credit task that converts a model into one or more requested formats; returns the task ID.

Create Creative Lab Build

Start a 3D build from a succeeded matching Creative Lab prototype.

Create Creative Lab Prototype

Start an entitled image-to-prototype task for a fixed Creative Lab product.

Create Image to 3D Task

Start a 3D generation task from one to four views of one object or a prior task's input images.

Create Image to Image Task

Start a credit-consuming task that edits or restyles one to five reference images from a text instruction.

Create Multi-Color Print Task

Start a 10-credit task that converts a GLB or FBX model from a prior Meshy task or direct URL into a limited-color 3MF for 3D printing, and return the task ID.

Create Print Analysis Task

Start a free task that analyzes a GLB, GLTF, OBJ, FBX, or STL model from a prior Meshy task or direct URL for printability defects and return the task ID.

Create Print Repair Task

Start a 10-credit task that repairs a GLB, GLTF, OBJ, FBX, or STL model from a prior Meshy task or direct URL for 3D printing and return the task ID.

Create Remesh Task

Start a 5-credit task that remeshes a model to the requested topology and polygon count, optionally resizes it, and exports the remeshed result in the requested formats.

Create Resize Task

Start a 1-credit task that scales a model by height, longest side, or automatic sizing and return the task ID.

Create Retexture Task

Start a credit-consuming task that applies one text, image, or multiview style source to an existing 3D model.

Create Rigging Task

Start a 5-credit task that rigs a GLB character with a biped or quadruped skeleton and return the task ID.

Create Text to 3D Task

Start a new Text to 3D preview or fused geometry-and-texture task and return its task ID.

Create Text to Image Task

Start a credit-consuming 2D image generation task from a text prompt.

Create Text to Motion Task

Start an entitled motion-generation task from a text prompt and return its task ID.

Create UV Unwrap Task

Start a 5-credit task that generates UV coordinates for a GLB model and return the task ID.

Delete Task

Delete a GA or Text-to-Motion task and its retained outputs.

Get Credit Balance

Return the connected Meshy account's available credit balance before starting paid generation tasks.

Get Task

Retrieve current status, errors, and available outputs for one task from a selected Meshy task family.

List Animation Library

Search or filter Meshy's unpaginated animation catalog and return action IDs for use when creating animation tasks.

List Tasks

Return one page of tasks for a selected Meshy task family, with a cursor for continuing to the next page.

List Usage Records

Return one page of terminal API-task usage and consumed credits for a Meshy team using a Studio or Enterprise team API key.

Refine Text to 3D Task

Apply texture to a succeeded Text to 3D preview and return the new refine task ID.

SETUP GUIDE

Connect Meshy MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["meshy"],
  mcp: true,
});
Create a session scoped to Meshy and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Generate photorealistic 3D model of chair",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Meshy request
SETUP GUIDE

Connect Meshy API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["meshy"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Meshy
3

Run Meshy tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Generate photorealistic 3D model of chair" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Meshy tool calls through the session, and print the final answer

Why Use Composio?

AI Native Meshy Integration

  • Supports both Meshy MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your Meshy data

Managed Auth

  • Built-in API key handling with secure storage
  • Central place to manage, scope, and revoke Meshy access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Meshy
  • Scoped, least privilege access to Meshy resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with Meshy.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Meshy tool your agent needs.Free to start.

Start building