Cincopa for AI agents
Cincopa manages video, image, and audio content, giving a marketing team a place to upload, organize, and embed multimedia across a site. 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 Cincopa.
Upload media from a URL
Upload an asset directly from a URL instead of downloading and re-uploading it manually.
Check an upload's status
Check the status of an in-progress asset upload before it gets embedded on a page.
Confirm the API connection
Validate the API connection is working before running a batch of media uploads.
5 Cincopa actions, graded by risk.
Every Cincopa 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.
- cincopa.get_upload_iframeGet Upload Iframe
- cincopa.pingValidate API Connection
write
3Create and change things. Allow, or ask the user first.
- cincopa.asset_upload_from_urlUpload Asset From URL
- cincopa.asset_upload_from_url_abortAbort Asset Upload From URL
- cincopa.asset_upload_from_url_get_statusGet Asset Upload From URL Status
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Cincopa in three steps.
- 01Your users connect CincopaThey add their Cincopa api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “upload Asset From URL” can wait for the user to approve.
- 03Any agent can actYour agent calls Cincopa through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('cincopa', { read: 'allow', write: 'ask', // asset_upload_from_url destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Cincopa connects.
Users add their Cincopa 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 Cincopa 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 Cincopa from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Cincopa and Arc0, answered.
Can I use Cincopa with Claude, ChatGPT or Cursor?
Yes. Connect Cincopa 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 Cincopa actions you allow.
How do users connect Cincopa?
Users add their Cincopa 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 Cincopa actions can my agent take?
5 in total: 2 read, 3 write and 0 destructive, such as “upload Asset From URL”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Cincopa?
Yes. Allow read actions and deny writes in the Cincopa policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Cincopa too?
Yes. The same Cincopa connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Cincopa into your agent.
Your users connect Cincopa once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan