Upload-Post for AI agents
Upload-Post publishes and schedules content across multiple social networks from one place, used by creators and marketing teams managing several channels at once. 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 Upload-Post.
Schedule a post across platforms
Queue a post to publish at a set time across connected social accounts.
Check upload status
Look up whether a scheduled post published successfully, a read-only check.
Confirm before canceling a scheduled post
Check with the user before canceling a scheduled post, since it removes it from the queue entirely.
12 Upload-Post actions, graded by risk.
Every Upload-Post action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- upload_post.list_profilesList Profiles
- upload_post.get_upload_statusGet Upload Status
- upload_post.list_upload_historyList Upload History
- upload_post.list_scheduled_postsList Scheduled Posts
- upload_post.list_cached_post_analyticsList Cached Post Analytics
- upload_post.list_platform_destinationsList Platform Destinations
write
5Create and change things. Allow, or ask the user first.
- upload_post.create_profileCreate Profile
- upload_post.update_scheduled_postUpdate Scheduled Post
- upload_post.enqueue_postEnqueue Post
- upload_post.publish_postPublish Post
- upload_post.schedule_postSchedule Post
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- upload_post.cancel_scheduled_postCancel Scheduled Post
Upload-Post in three steps.
- 01Your users connect Upload-PostThey add their Upload-Post api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Profile” can wait for the user, and “cancel Scheduled Post” can be denied outright.
- 03Any agent can actYour agent calls Upload-Post through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('upload_post', { read: 'allow', write: 'ask', // create_profile destructive: 'deny', // cancel_scheduled_post }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Upload-Post connects.
Users add their Upload-Post 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 Upload-Post 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 Upload-Post from any agent.
Upload-Post and Arc0, answered.
Can I use Upload-Post with Claude, ChatGPT or Cursor?
Yes. Connect Upload-Post 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 Upload-Post actions you allow.
How do users connect Upload-Post?
Users add their Upload-Post 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 Upload-Post actions can my agent take?
12 in total: 6 read, 5 write and 1 destructive, such as “create Profile”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Upload-Post?
Yes. Actions like “cancel Scheduled Post” 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 Upload-Post too?
Yes. The same Upload-Post connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Upload-Post into your agent.
Your users connect Upload-Post once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan