Ordinal for AI agents
Ordinal is a collaborative social media planning platform for creating, reviewing, and scheduling content across connected channels. Content and marketing teams use it to plan campaigns together. 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 Ordinal.
Schedule a post for publishing
Set a post to go live on a connected channel at a chosen date and time.
Check profile analytics read-only
Pull engagement analytics for a profile before deciding what content to plan next.
Unschedule a post with approval
Pull a scheduled post back from the queue only after a reviewer flags a concern.
13 Ordinal actions, graded by risk.
Every Ordinal action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- ordinal.get_postGet Post
- ordinal.list_ideasList Ideas
- ordinal.list_postsList Posts
- ordinal.list_labelsList Labels
- ordinal.get_workspaceGet Workspace
- ordinal.list_profilesList Profiles
- ordinal.get_profile_analyticsGet Profile Analytics
write
6Create and change things. Allow, or ask the user first.
- ordinal.create_ideaCreate Idea
- ordinal.create_postCreate Post
- ordinal.update_postUpdate Post
- ordinal.add_idea_to_calendarAdd Idea To Calendar
- ordinal.schedule_postSchedule Post
- ordinal.unschedule_postUnschedule Post
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Ordinal in three steps.
- 01Your users connect OrdinalThey add their Ordinal api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Idea” can wait for the user to approve.
- 03Any agent can actYour agent calls Ordinal through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ordinal', { read: 'allow', write: 'ask', // create_idea destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ordinal connects.
Users add their Ordinal 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 Ordinal 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 Ordinal from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Ordinal and Arc0, answered.
Can I use Ordinal with Claude, ChatGPT or Cursor?
Yes. Connect Ordinal 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 Ordinal actions you allow.
How do users connect Ordinal?
Users add their Ordinal 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 Ordinal actions can my agent take?
13 in total: 7 read, 6 write and 0 destructive, such as “create Idea”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Ordinal?
Yes. Allow read actions and deny writes in the Ordinal policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Ordinal too?
Yes. The same Ordinal connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ordinal into your agent.
Your users connect Ordinal once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan