What it does

Generates 3D models and textures through Meshy's API and returns asset URLs. The output is usable for game jams, prototypes, and background props; it is not production topology, and every asset needs a look before it ships. Generation is asynchronous, so the agent has to poll rather than wait.

Install

Terminal

npx -y @meshy-ai/meshy-mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "meshy": {
      "command": "npx",
      "args": [
        "-y",
        "@meshy-ai/meshy-mcp-server"
      ]
    }
  }
}

Use it for

Generating 3D assets from text or images inside an agent workflow

Skip it if

Production pipelines that need deterministic, editable topology

When to use it

Reach for this when the task needs 3d inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Meshy MCP