Transloadit for AI agents
Transloadit processes uploaded files, images, audio, and video through programmable workflows, used by developers who need media processing without running their own infrastructure. 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 Transloadit.
Create a processing assembly
Start a file processing job, like resizing images or transcoding video, on an uploaded file.
Check an assembly's status
Look up whether a processing job has finished, a read-only status check.
Confirm before canceling an assembly
Check with the user before canceling a running assembly, since partial output may be lost.
6 Transloadit actions, graded by risk.
Every Transloadit action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- transloadit.list_assembliesList Assemblies
- transloadit.get_assembly_statusGet Assembly Status
write
3Create and change things. Allow, or ask the user first.
- transloadit.create_assemblyCreate Assembly
- transloadit.replay_assemblyReplay Assembly
- transloadit.replay_assembly_notificationReplay Assembly Notification
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- transloadit.cancel_assemblyCancel Assembly
Transloadit in three steps.
- 01Your users connect TransloaditThey add their Transloadit api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Assembly” can wait for the user, and “cancel Assembly” can be denied outright.
- 03Any agent can actYour agent calls Transloadit through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('transloadit', { read: 'allow', write: 'ask', // create_assembly destructive: 'deny', // cancel_assembly }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Transloadit connects.
Users add their Transloadit 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 Transloadit 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 Transloadit from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Transloadit and Arc0, answered.
Can I use Transloadit with Claude, ChatGPT or Cursor?
Yes. Connect Transloadit 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 Transloadit actions you allow.
How do users connect Transloadit?
Users add their Transloadit 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 Transloadit actions can my agent take?
6 in total: 2 read, 3 write and 1 destructive, such as “create Assembly”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Transloadit?
Yes. Actions like “cancel Assembly” 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 Transloadit too?
Yes. The same Transloadit connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Transloadit into your agent.
Your users connect Transloadit once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan