Unipile for AI agents
Unipile provides one API for messaging, email, calendar, and social accounts, used by developers who need a single connection instead of one per provider. 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 Unipile.
List connected accounts
Pull the accounts connected through Unipile as a read-only inventory check.
Check an account's connection status
Verify a specific account is still authenticated before sending through it.
Review accounts before adding a new integration
Read the current account list before deciding whether a new provider needs to be connected.
1 Unipile actions, graded by risk.
Every Unipile action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- unipile.list_accountsList Accounts
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Unipile in three steps.
- 01Your users connect UnipileThey add their Unipile api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Unipile through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('unipile', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Unipile connects.
Users add their Unipile 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 Unipile 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 Unipile from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Unipile and Arc0, answered.
Can I use Unipile with Claude, ChatGPT or Cursor?
Yes. Connect Unipile 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 Unipile actions you allow.
How do users connect Unipile?
Users add their Unipile 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 Unipile actions can my agent take?
1 in total: 1 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Unipile?
Yes. Allow read actions and deny writes in the Unipile policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Unipile too?
Yes. The same Unipile connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Unipile into your agent.
Your users connect Unipile once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan