OnlySocial for AI agents
OnlySocial is a social media management tool for organizing accounts, media, tags, and posts across a shared workspace. Small marketing teams use it to plan and publish content 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 OnlySocial.
Upload media for a post
Upload an image or video asset so it is ready to attach to a scheduled post.
Tag posts for organization
Create and apply a tag to group related posts by campaign or topic.
Check scheduled posts read-only
List upcoming posts to confirm nothing conflicts before adding a new one to the calendar.
10 OnlySocial actions, graded by risk.
Every OnlySocial 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.
- onlysocial.get_postGet Post
- onlysocial.get_mediaGet Media
- onlysocial.list_tagsList Tags
- onlysocial.list_mediaList Media
- onlysocial.list_postsList Posts
- onlysocial.list_accountsList Social Accounts
write
3Create and change things. Allow, or ask the user first.
- onlysocial.create_tagCreate Tag
- onlysocial.update_tagUpdate Tag
- onlysocial.upload_mediaUpload Media
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- onlysocial.delete_tagDelete Tag
OnlySocial in three steps.
- 01Your users connect OnlySocialThey add their OnlySocial api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete Tag” can be denied outright.
- 03Any agent can actYour agent calls OnlySocial through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('onlysocial', { read: 'allow', write: 'ask', // create_tag destructive: 'deny', // delete_tag }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How OnlySocial connects.
Users add their OnlySocial 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 OnlySocial 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 OnlySocial from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
OnlySocial and Arc0, answered.
Can I use OnlySocial with Claude, ChatGPT or Cursor?
Yes. Connect OnlySocial 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 OnlySocial actions you allow.
How do users connect OnlySocial?
Users add their OnlySocial 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 OnlySocial actions can my agent take?
10 in total: 6 read, 3 write and 1 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in OnlySocial?
Yes. Actions like “delete Tag” 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 OnlySocial too?
Yes. The same OnlySocial connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug OnlySocial into your agent.
Your users connect OnlySocial once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan