meshy-mcp-server
MCP server for Meshy AI 3D generation platform
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/meshy-dev/meshy-mcp-server with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/meshy-dev/meshy-mcp-server'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/meshy-dev--meshy-mcp-server)HTML
<a href="/listings/meshy-dev--meshy-mcp-server"><img src="/api/listings/meshy-dev--meshy-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Pick whichever fits your workflow — they all produce the same config.
Option 1 · One-Command Install · Recommended
[`add-mcp`](https://github.com/neondatabase/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](#activate-after-install) 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
<details> <summary><b>Cursor</b></summary>
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"]`.
</details>
<details> <summary><b>Claude Code</b></summary>
claude mcp add-json meshy '{"command":"npx","args":["-y","@meshy-ai/meshy-mcp-server"],"env":{"MESHY_API_KEY":"msy_YOUR_API_KEY"}}'</details>
<details> <summary><b>Other clients</b> (Windsurf, Claude Desktop, Codex, VS Code, Cline…)</summary>
Use **Option 1** — `add-mcp` writes the correct config for each.
</details>
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 224 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Meshy MCP Server
- [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for the [Meshy AI](https://www.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:
- | Category | Tools |
- |----------|-------|
- | **3D Generation** | `meshy_text_to_3d`, `meshy_text_to_3d_refine`, `meshy_image_to_3d`, `meshy_multi_image_to_3d` |
- | **Creative Lab** | `meshy_creative_lab` (9 products) |
- | **Post-Processing** | `meshy_remesh`, `meshy_retexture` |
- | **Rigging & Animation** | `meshy_rig`, `meshy_animate`, `meshy_text_to_motion`, `meshy_list_animations` |
- | **Conversion** | `meshy_convert`, `meshy_resize`, `meshy_uv_unwrap` |
- | **Image Generation** | `meshy_text_to_image`, `meshy_image_to_image` |
- | **Task Management** | `meshy_get_task_status`, `meshy_list_tasks`, `meshy_cancel_task`, `meshy_download_model` |
- | **Workspace** | `meshy_list_models` |
- | **3D Printing** | `meshy_send_to_slicer`, `meshy_analyze_printability`, `meshy_repair_printability`, `meshy_process_multicolor`, `meshy_auto_split` |
- | **Account** | `meshy_check_balance`, `meshy_list_usage` |
- ### 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 unless `texture_model: "meshy-7"`) on every generation endpoint
- - **Smart Topology**: `model_type: "smart-topology"` on text-to-3d (new in v0.6.0) and image-to-3d. Clean, part-separated triangle mesh generated directly at `target_polycount`, for 5 credits of mesh. `meshy-t2.5` (v0.6.4; the default since v0.6.10) is the newest Smart Topology model, with sharper detail for game assets: 100–30,000 faces (default 15,000). `ai_model: "meshy-t2"` is still available: 100–15,000 faces (default 4,000), 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 views of the *same object*, front view first, drive the texture instead of a single style reference (requires Meshy 7 or Meshy N1)
- - **Texture model on image / multi-image to 3D**: `texture_model` picks the texture model apart from the geometry, in the same task and at the same price: `meshy-7` (PBR, up to 8K), `meshy-n1` (2K base color from reference images only) or `meshy-6-lite` (2K, single-image only). Omitted, the geometry's default is used. Options a texture model can't do (for example `meshy-n1` with `texture_prompt`, `enable_pbr: true` or 4K) are refused before any request. The tool descriptions and server instructions carry a short "choose models by project" guide, with the [Models](https://docs.meshy.ai/en/api/models) page for detail
- - **Meshy N1 Retexture**: `ai_model: "meshy-n1"` on `meshy_retexture` — a 2K base color texture from reference images only: one image (`image_style_url`, read as the front view) or 1–4 views (`multiview_image_urls`, front first, the rest in any order). 10 credits. No text prompt, PBR maps, 4K/8K or `remove_lighting`: the tool refuses those before any request
- - **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 a printed `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](https://docs.meshy.ai/en/api/text-to-3d), [image](https://docs.meshy.ai/en/api/image-to-3d), [multi-image](https://docs.meshy.ai/en/api/multi-image-to-3d), [retexture](https://docs.meshy.ai/en/api/retexture)):
- | Endpoint | Accepted `ai_model` | `latest` resolves to |
- |---|---|---|
- | `meshy_text_to_3d` / `_refine` | `meshy-7.1`, `meshy-6`, `meshy-6-lite`, `latest` — plus `meshy-t2` / `meshy-t2.5` with `model_type: "smart-topology"` (preview only) | Meshy 7.1 |
- | `meshy_image_to_3d` | `meshy-7.1`, `meshy-6`, `meshy-6-lite`, `latest` — plus `meshy-t2` / `meshy-t2.5` with `model_type: "smart-topology"` | Meshy 7.1 |
- | `meshy_multi_image_to_3d` | `meshy-7.1`, `meshy-6`, `meshy-6-lite`, `latest` (no Smart Topology) | Meshy 7.1 |
- | `meshy_retexture` | `meshy-7`, `meshy-6`, `meshy-6-lite`, `meshy-n1` (image-only, 2K base color), `latest` (no `meshy-7.1`) | Meshy 7 |
- `meshy_image_to_3d` also takes `texture_model` (`meshy-7`, `meshy-n1`, `meshy-6-lite`) and `meshy_multi_image_to_3d` takes `meshy-7` or `meshy-n1`. Without it, Meshy 7.1 / `latest` / Smart Topology texture with Meshy 7, `meshy-6` with Meshy 6 and `meshy-6-lite` with Meshy 6 Lite. Which pair to pick per project: [Models](https://docs.meshy.ai/en/api/models#choose-by-project).
- Legacy id still accepted: `meshy-7` on generation (deprecated, billed like `meshy-7.1`). `meshy-5` and Meshy T1 (`meshy-t1`, `model_type: "lowpoly"`) are retired and no longer accepted; use `meshy-6-lite` and `smart-topology` + `meshy-t2.5`.
- Generation cost ([pricing](https://docs.meshy.ai/en/api/pricing)):
- | `ai_model` | Mesh only | + 2K/4K texture | + 8K texture |
- |---|---|---|---|
- | `meshy-7.1` / `latest` | 20 | 30 | 35 |
- | `meshy-6` | 20 | 30 | 35 |
- | `meshy-6-lite` | 5 | 15 | 20 (`texture_model: "meshy-7"` only) |
- | `meshy-t2` / `meshy-t2.5` (smart-topology, single-image) | 5 | 15 | 20 |
- `texture_model` doesn't change the price: a textured task costs the mesh plus the texture at its resolution. 4K / 8K need the Meshy 7 or Meshy 6 texture model. 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"`.
- 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-t2.5`. 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); Meshy N1 (`meshy-n1`) is 10 credits and 2K only. 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.
- ## Prerequisites
- - Node.js >= 18
- - A Meshy API key ([get one here](https://www.meshy.ai/developers/keys) — 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`](https://github.com/neondatabase/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:
- ```bash
- npx add-mcp @meshy-ai/meshy-mcp-server --env MESHY_API_KEY=msy_YOUR_API_KEY
- ```
- After it finishes, jump to [Activate](#activate-after-install) 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
- <details>
- <summary><b>Cursor</b></summary>
- Paste into `.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global):
- ```json
- {
- "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"]`.
- </details>
- <details>
- <summary><b>Claude Code</b></summary>
- ```bash
- claude mcp add-json meshy '{"command":"npx","args":["-y","@meshy-ai/meshy-mcp-server"],"env":{"MESHY_API_KEY":"msy_YOUR_API_KEY"}}'
- ```
- </details>
- <details>
- <summary><b>Other clients</b> (Windsurf, Claude Desktop, Codex, VS Code, Cline…)</summary>
- Use **Option 1** — `add-mcp` writes the correct config for each.
- </details>
- ## Activate After Install
- Most clients auto-load the new server, but **Cursor and VS Code require a manual toggle**:
- | Client | What to do | Verify |
- |---|---|---|
- | **Cursor** | Restart → `Settings` → `MCP & Integrations` → toggle `meshy` **on** → wait for green dot ● → open a **new chat** | `List the meshy tools available` |
- | **Claude Code** | Nothing — auto-loads on next message | `/mcp` shows `meshy ✓ connected` |
- | **Claude Desktop** | Quit & relaunch the app | `List the meshy tools available` |
- | **Windsurf** | Refresh in the Cascade panel's MCP section | `List the meshy tools available` |
- | **VS Code** | Run command `MCP: List Servers` → click `meshy` → **Start** | `List the meshy tools available` |
- | **Codex** | Nothing — auto-loads on next session | `List the meshy tools available` |
- ## 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
- | Environment Variable | Description | Default |
- |---------------------|-------------|---------|
- | `MESHY_API_KEY` | **Required.** Your Meshy API key (starts with `msy_`) | — |
- | `MESHY_API_HOST` | API base URL | `https://api.meshy.ai` |
- | `TRANSPORT` | Transport mode: `stdio` or `http` | `stdio` |
- | `PORT` | Port for HTTP transport | `3000` |
- | `CHARACTER_LIMIT` | Max response size in characters | `25000` |
- | `MESHY_CLIENT` | Optional. Identifies the integrating app in Meshy's logs, format `name/version` (e.g. `hermes-meshy-plugin/0.4.0`) | — |
- ## Development
- ```bash
- # 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](docs/maintenance.md) 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:
- ```bash
- TRANSPORT=http PORT=3000 npm start
- ```
- Endpoints:
- - `POST /mcp` — MCP protocol endpoint
- - `GET /health` — Health check
- ## License
- [MIT](LICENSE)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.