Meshy for AI agents

Meshy generates 3D models, textures, and animations from text or images through an API for games, product, and print workflows. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

AI and modelsAPI keyMCP + RESTmeshy.ai
AUDIT LOG · MESHYPOLICY: acme-support
09:41:07 · claude · u_8f2read
meshy.list_tasks
List Tasks✓ allowed · 212ms
09:41:08 · claude · u_8f2read
meshy.get_task
Get Task✓ allowed · 164ms
09:41:09 · claude · u_8f2write
meshy.create_remesh_task
Create Remesh Task✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
meshy.delete_task
Delete Task✕ blocked · policy: deny
EVERY MESHY CALL, ON THE RECORD
01 · USE CASES

What agents do in Meshy.

01

Generate a 3D model from text

Create a draft 3D model from a text description for a product concept.

02

Check a generation task's status

Look up whether a submitted 3D generation task has finished before downloading its output, a read-only check.

03

Check remaining credit balance

Look up account credits before starting a batch of 3D generation tasks.

02 · ACTIONS

27 Meshy actions, graded by risk.

Every Meshy action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • meshy.get_task
    Get Task
  • meshy.list_tasks
    List Tasks
  • meshy.get_credit_balance
    Get Credit Balance
  • meshy.list_usage_records
    List Usage Records
  • meshy.list_animation_library
    List Animation Library

write

20

Create and change things. Allow, or ask the user first.

  • meshy.create_remesh_task
    Create Remesh Task
  • meshy.create_resize_task
    Create Resize Task
  • meshy.create_convert_task
    Create Convert Task
  • meshy.create_rigging_task
    Create Rigging Task
  • meshy.create_animation_task
    Create Animation Task
  • meshy.create_retexture_task
    Create Retexture Task
  • meshy.create_uv_unwrap_task
    Create UV Unwrap Task
  • meshy.create_auto_split_task
    Create Auto Split Task
  • meshy.create_text_to_3d_task
    Create Text to 3D Task
  • meshy.create_image_to_3d_task
    Create Image to 3D Task
  • meshy.create_print_repair_task
    Create Print Repair Task
  • meshy.create_creative_lab_build
    Create Creative Lab Build
  • meshy.create_text_to_image_task
    Create Text to Image Task
  • meshy.create_image_to_image_task
    Create Image to Image Task
  • meshy.create_print_analysis_task
    Create Print Analysis Task
  • meshy.create_text_to_motion_task
    Create Text to Motion Task
+ 4 MORE

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • meshy.delete_task
    Delete Task
  • meshy.cancel_creative_lab_task
    Cancel Creative Lab Task
03 · HOW IT WORKS

Meshy in three steps.

  1. 01Your users connect MeshyThey add their Meshy api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Remesh Task” can wait for the user, and “delete Task” can be denied outright.
  3. 03Any agent can actYour agent calls Meshy through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('meshy', {
  read: 'allow',
  write: 'ask',        // create_remesh_task
  destructive: 'deny',  // delete_task
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Meshy connects.

Users add their Meshy api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Meshy connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Meshy from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Meshy and Arc0, answered.

Q01

Can I use Meshy with Claude, ChatGPT or Cursor?

Yes. Connect Meshy to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Meshy actions you allow.

Q02

How do users connect Meshy?

Users add their Meshy api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Meshy actions can my agent take?

27 in total: 5 read, 20 write and 2 destructive, such as “create Remesh Task”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Meshy?

Yes. Actions like “delete Task” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Meshy too?

Yes. The same Meshy connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Meshy into your agent.

Your users connect Meshy once, under your brand. Your agent gets 27 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan