Luma Labs for AI agents
Luma Labs is an AI media platform for generating and editing images and video, including reframing and layer extraction for creative production work. 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.
What agents do in Luma Labs.
Generate an image from a prompt
Create a draft image from a text prompt for a creative concept.
Check a generation's status
Look up whether a submitted video or image generation has finished, read-only.
Approve before deleting a file
Require approval before deleting a generated file, since it may still be referenced elsewhere.
11 Luma Labs actions, graded by risk.
Every Luma Labs action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- luma_labs.get_fileGet File
- luma_labs.list_filesList Files
- luma_labs.get_generationGet Generation
- luma_labs.extract_image_layersExtract Image Layers
write
6Create and change things. Allow, or ask the user first.
- luma_labs.edit_imageEdit Image
- luma_labs.edit_videoEdit Video
- luma_labs.upload_fileUpload File
- luma_labs.reframe_videoReframe Video
- luma_labs.generate_imageGenerate Image
- luma_labs.generate_videoGenerate Video
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- luma_labs.delete_fileDelete File
Luma Labs in three steps.
- 01Your users connect Luma LabsThey add their Luma Labs api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “edit Image” can wait for the user, and “delete File” can be denied outright.
- 03Any agent can actYour agent calls Luma Labs through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('luma_labs', { read: 'allow', write: 'ask', // edit_image destructive: 'deny', // delete_file }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Luma Labs connects.
Users add their Luma Labs 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 Luma Labs 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
Use Luma Labs from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Luma Labs and Arc0, answered.
Can I use Luma Labs with Claude, ChatGPT or Cursor?
Yes. Connect Luma Labs 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 Luma Labs actions you allow.
How do users connect Luma Labs?
Users add their Luma Labs 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.
Which Luma Labs actions can my agent take?
11 in total: 4 read, 6 write and 1 destructive, such as “edit Image”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Luma Labs?
Yes. Actions like “delete File” 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.
Can my own backend call Luma Labs too?
Yes. The same Luma Labs connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Luma Labs into your agent.
Your users connect Luma Labs once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan