OneUp for AI agents
OneUp is a social media management platform for scheduling posts, managing comments, and reviewing analytics across multiple networks. Social and marketing teams use it to run one calendar for every channel. 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 OneUp.
Schedule a post across channels
Create and schedule a post to publish across connected social accounts at a chosen time.
Check content performance read-only
Pull content analytics for recent posts before deciding what to promote further.
Reply to a comment
Post a reply to a comment thread on a published post to keep engagement moving.
27 OneUp actions, graded by risk.
Every OneUp action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
15Look things up. Allowed by default.
- oneup.list_postsList Posts
- oneup.list_categoriesList Categories
- oneup.list_comment_repliesList Comment Replies
- oneup.list_comment_threadsList Comment Threads
- oneup.list_social_accountsList Social Accounts
- oneup.get_content_analyticsGet Content Analytics
- oneup.list_pinterest_boardsList Pinterest Boards
- oneup.get_analytics_overviewGet Analytics Overview
- oneup.get_meta_ads_analyticsGet Meta Ads Analytics
- oneup.list_category_accountsList Category Accounts
- oneup.list_youtube_playlistsList YouTube Playlists
- oneup.get_audience_demographicsGet Audience Demographics
- oneup.get_google_business_reviewsGet Google Business Reviews
- oneup.list_tiktok_trending_soundsList TikTok Trending Sounds
- oneup.list_instagram_trending_soundsList Instagram Trending Sounds
write
10Create and change things. Allow, or ask the user first.
- oneup.create_text_postCreate Text Post
- oneup.create_image_postCreate Image Post
- oneup.create_video_postCreate Video Post
- oneup.create_media_upload_urlCreate Media Upload URL
- oneup.comment_on_postComment On Post
- oneup.refresh_commentsRefresh Comments
- oneup.reply_to_commentReply To Comment
- oneup.refresh_analyticsRefresh Analytics
- oneup.edit_scheduled_postEdit Scheduled Post
- oneup.reschedule_failed_postReschedule Failed Post
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- oneup.delete_commentDelete Comment
- oneup.delete_scheduled_postDelete Scheduled Post
OneUp in three steps.
- 01Your users connect OneUpThey add their OneUp api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Text Post” can wait for the user, and “delete Comment” can be denied outright.
- 03Any agent can actYour agent calls OneUp through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('oneup', { read: 'allow', write: 'ask', // create_text_post destructive: 'deny', // delete_comment }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How OneUp connects.
Users add their OneUp 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 OneUp 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 OneUp from any agent.
OneUp and Arc0, answered.
Can I use OneUp with Claude, ChatGPT or Cursor?
Yes. Connect OneUp 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 OneUp actions you allow.
How do users connect OneUp?
Users add their OneUp 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 OneUp actions can my agent take?
27 in total: 15 read, 10 write and 2 destructive, such as “create Text Post”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in OneUp?
Yes. Actions like “delete Comment” 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 OneUp too?
Yes. The same OneUp connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug OneUp into your agent.
Your users connect OneUp once, under your brand. Your agent gets 27 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan