CloudConvert for AI agents
CloudConvert converts files between over 200 formats, letting a workflow turn a document, image, or video into whatever format it actually needs. 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 CloudConvert.
Check supported formats
Check which formats a file type can convert to before setting up a conversion job.
Export a converted file to storage
Export a converted file directly to cloud storage instead of downloading it manually.
Check a task's progress
List running tasks to check whether a batch conversion job has finished.
9 CloudConvert actions, graded by risk.
Every CloudConvert action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- cloudconvert.list_tasksList Tasks
- cloudconvert.list_webhooksList Webhooks
- cloudconvert.list_operationsList Operations
- cloudconvert.list_supported_formatsList Supported Formats
- cloudconvert.show_userShow User
write
3Create and change things. Allow, or ask the user first.
- cloudconvert.create_webhookCreate Webhook
- cloudconvert.create_export_s3_taskCreate Export S3 Task
- cloudconvert.create_export_google_cloud_storage_taskCreate Export Google Cloud Storage Task
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- cloudconvert.delete_webhookDelete Webhook
CloudConvert in three steps.
- 01Your users connect CloudConvertThey add their CloudConvert api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Webhook” can wait for the user, and “delete Webhook” can be denied outright.
- 03Any agent can actYour agent calls CloudConvert through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('cloudconvert', { read: 'allow', write: 'ask', // create_webhook destructive: 'deny', // delete_webhook }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How CloudConvert connects.
Users add their CloudConvert 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 CloudConvert 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 CloudConvert from any agent.
CloudConvert and Arc0, answered.
Can I use CloudConvert with Claude, ChatGPT or Cursor?
Yes. Connect CloudConvert 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 CloudConvert actions you allow.
How do users connect CloudConvert?
Users add their CloudConvert 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 CloudConvert actions can my agent take?
9 in total: 5 read, 3 write and 1 destructive, such as “create Webhook”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in CloudConvert?
Yes. Actions like “delete Webhook” 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 CloudConvert too?
Yes. The same CloudConvert connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug CloudConvert into your agent.
Your users connect CloudConvert once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan