Meshy MCP Server

Model Context Protocol (MCP) server for the Meshy AI 3D generation platform. Enables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation.

Features

28 tools covering the full Meshy API:

Key Capabilities

• Safe retries (v0.6.3): a create request is never resent after a timeout or server error, so a task is never created and billed twice; status checks retry at the API's suggested interval

• Text to 3D: Generate 3D models from text descriptions (preview + refine pipeline)

• Image to 3D: Convert single or multiple images into 3D models

• Meshy 7.1 (v0.6.0): ai_model: "meshy-7.1" (and latest) on text-to-3d, image-to-3d and multi-image-to-3d. geometry_resolution: "standard" | "2k" | "4k" picks the geometry pass (+5 credits for 2k/4k; multi-image supports standard/2k). ultra_mode is deprecated

• Meshy 6 Lite (v0.6.0): ai_model: "meshy-6-lite" — fast, 5-credit mesh (15 textured, 2K textures only) on every generation endpoint

• Smart Topology: model_type: "smart-topology" with ai_model: "meshy-t2" on text-to-3d (new in v0.6.0) and image-to-3d. Clean, part-separated triangle mesh generated directly at 100–15,000 faces (default 4,000) for 5 credits of mesh. meshy-t2.5 (v0.6.4) is the newest Smart Topology model, with sharper detail for game assets: 100–30,000 faces (default 15,000), same cost

• Multi-view texture on multi-image (v0.6.0): texture_image_urls — 1–4 views of the same object drive the texture (Meshy 7.1)

• 8K Textures (v0.5.0): texture_resolution: "2k" | "4k" | "8k" on image-to-3d, multi-image-to-3d, text-to-3d refine and retexture (8K costs 15 credits vs 10). Replaces the now-deprecated hd_texture flag

• Multi-view Retexture (v0.5.0): multiview_image_urls — 1–4 ordered views of the same object drive the texture instead of a single style reference (requires Meshy 7)

• Auto-Rigging & Animation: Add skeletons and animations to humanoid characters. meshy_animate takes one preset action, up to 10 actions as clips in one file, or a generated motion (v0.6.3); meshy_list_animations finds action ids

• Text to Motion (v0.6.3): generate a motion clip from a description (prime FBX, 10 credits / swift BVH, 3 credits) and apply it to a rigged character

• Creative Lab: One tool — a photo → a finished, print-ready product. 9 products: figure, lamp, keychain (with engraved name_text), fridge-magnet, vinyl-figure, brick-figure, keycap, and (v0.6.3) fidget-pixel and fidget-collapsible. Runs the whole pipeline and returns only the final 3D model; build options and output format are configurable

• Format & Size Utilities: convert (format conversion incl. 3MF, 1 credit), resize (real-world dimensions, 1 credit), uv_unwrap (clean UV layout for external texturing, 5 credits)

• 2D Image Models: text_to_image / image_to_image support nano-banana, nano-banana-2, nano-banana-2-lite, nano-banana-2-1, nano-banana-pro, gpt-image-2, gpt-image-2-5-flare and gpt-image-2-5-sunburst, with transparent-background output (remove_background). Image-to-image can edit an earlier result by input_task_id

• 3D Printability Suite:

  • analyze_printability — free check (watertight, volume, holes, non-manifold edges, degenerate faces), plus a wall-thickness check for a given printer type and print size (v0.6.3)

  • repair_printability — 10-credit topology repair (.glb / .gltf / .obj / .fbx / .stl) that can also thicken thin walls

  • process_multicolor — 10-credit multi-color 3MF for AMS/MMU printers, realistic or cartoon style, with a slicer preset for 9 printer brands

  • auto_split (v0.6.3) — 10 credits: cut a model into printable parts automatically, by named parts, or by color, with optional connectors

• Usage reporting (v0.6.3): list_usage lists finished API tasks with their credits (Studio / Enterprise teams)

• Task and model listing (v0.6.3): list_tasks lists tasks of any status from text-to-3d, image-to-3d, multi-image-to-3d, text-to-image and image-to-image by default (pass task_types for printing, rigging, animation, motion, post-processing or Creative Lab tasks); list_models lists finished 3D models of any model-producing type (image-to-3d by default), each with the task_type and formats to download. Before 0.6.3, list_tasks queried every type and list_models listed text-to-3d only; see the CHANGELOG's behavior changes

• Slicer Integration: Auto-detect 7 installed slicers (OrcaSlicer, Bambu, Creality, Elegoo, Anycubic, PrusaSlicer, Cura; all but Cura open multi-color 3MF) and return launch commands the agent can execute

• Smart File Organization: Auto-saves to meshy_output/ with project folders, metadata, and history tracking

• Built-in Workflow Intelligence: Server instructions guide the agent through correct tool chains for each use case

Models & Credits

ai_model is not the same set on every endpoint, and latest does not resolve to the same model everywhere (text, image, multi-image, retexture):

Legacy ids still accepted: meshy-7 on generation (deprecated, billed like meshy-7.1) and single-image meshy-t1 (deprecated; use meshy-t2). meshy-5 is retired and no longer accepted.

Generation cost (pricing):

Text-to-3D preview is billed mesh-only; refine adds 10 (15 at 8K). geometry_resolution: "2k" or "4k" (Ultra pass, Meshy 7.1 / latest) adds +5; multi-image supports "2k" only. ultra_mode is deprecated and maps to "2k". model_type: "lowpoly" retires on 2026-10-30: use smart-topology + meshy-t2.

Smart Topology generates directly at target_polycount and skips remeshing: meshy-t2 100–15,000 faces (default 4,000), meshy-t2.5 100–30,000 (default 15,000). Without ai_model, model_type: "smart-topology" uses meshy-t2. Output is triangle-only. For standard models, target_polycount needs should_remesh: true and is overridden by decimation_mode.

Retexture is 10 credits (15 at 8K). Creative Lab is 36 credits per product (6 + 30; lamp is 30 + 6) except keycap, 62 (12 + 50) and fidget-collapsible, 6 (single stage). Images: nano-banana 3, nano-banana-2 6, nano-banana-2-lite 3, nano-banana-2-1 4, nano-banana-pro 9, GPT Image models 9 (text) / 12 (image). Other tools: remesh 5, rig 5, animate 3 per action, text-to-motion 10 (prime) / 3 (swift), convert 1, resize 1, uv-unwrap 5, analyze-printability free, repair-printability 10, multicolor 10, auto-split 10.

Related MCP server: Meshy MCP Server

Prerequisites

• Node.js >= 18

• A Meshy API key (get one here — requires Pro plan or above)

Installation

Pick whichever fits your workflow — they all produce the same config.

Option 1 · One-Command Install · Recommended

add-mcp auto-detects every AI client on your machine (Cursor, Claude Code, Claude Desktop, Windsurf, Codex, VS Code, Cline, …) and writes the right config to each:

npx add-mcp @meshy-ai/meshy-mcp-server --env MESHY_API_KEY=msy_YOUR_API_KEY

After it finishes, jump to Activate for your client.

Option 2 · Install by Asking Your AI Agent

Already chatting with Cursor / Claude Code / Codex? Paste this prompt:

Install the Meshy MCP server for me. Docs: https://github.com/meshy-dev/meshy-mcp-server
Use this env var: MESHY_API_KEY=msy_YOUR_API_KEY

The agent will run add-mcp (or write mcp.json directly) and tell you when it's ready. You'll still need the Activate step for your client.

Option 3 · Manual Install

Paste into .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

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

Windows: replace "command": "npx" with "command": "cmd" and "args": ["/c", "npx", "-y", "@meshy-ai/meshy-mcp-server"].

claude mcp add-json meshy '{"command":"npx","args":["-y","@meshy-ai/meshy-mcp-server"],"env":{"MESHY_API_KEY":"msy_YOUR_API_KEY"}}'

Use Option 1 — add-mcp writes the correct config for each.

Activate After Install

Most clients auto-load the new server, but Cursor and VS Code require a manual toggle:

Troubleshooting

• MESHY_API_KEY environment variable is required — returned by every tool when the key didn't reach the server. Make sure it sits inside an "env": {...} block in your mcp.json, not in args. Restart the server after fixing it.

• spawn npx ENOENT (Windows) — wrap with cmd /c (see Cursor block above).

• error: unknown option '-y' (Claude Code on Windows) — use claude mcp add-json instead of claude mcp add … -- npx -y ….

• Cursor doesn't list meshy — make sure mcp.json is valid JSON (no trailing commas), then fully restart Cursor.

• Authentication failed: the Meshy API rejected MESHY_API_KEY (401) — the key is mistyped, revoked or expired. Regenerate at https://www.meshy.ai/developers/keys, update your config and restart the server.

Configuration

Development

# Clone and install
git clone https://github.com/meshy-dev/meshy-mcp-server.git
cd meshy-mcp-server
npm ci

# Development with hot reload
npm run dev

# Build
npm run build

# Type check
npm run lint

# Build and run offline mocked-request tests (no API key or credits required)
npm test

# Run
npm start

Maintaining a local checkout

See setup, updates, and rollback for running a reviewed local build, pinning package versions, testing model routing without paid API calls, and reconnecting a client safely.

HTTP Transport

For remote access, run in HTTP mode:

TRANSPORT=http PORT=3000 npm start

Endpoints:

• POST /mcp — MCP protocol endpoint

• GET /health — Health check

License

MIT