Proxiedmail for AI agents
ProxiedMail offers privacy-focused email addresses that forward messages through webhooks without exposing a real inbox. Developers use it to receive email programmatically while protecting privacy. 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 Proxiedmail.
Check proxy bindings read-only
List active proxy email bindings to confirm which addresses are still forwarding.
Set up a webhook receiver
Create a webhook so incoming email to a proxy address is delivered automatically.
Update a proxy binding with approval
Change where a proxy address forwards to only after the owner confirms the new destination.
5 Proxiedmail actions, graded by risk.
Every Proxiedmail action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- proxiedmail.get_api_tokenGet API Token
- proxiedmail.get_webhook_dataGet webhook data
- proxiedmail.list_proxy_bindingsList proxy bindings
write
2Create and change things. Allow, or ask the user first.
- proxiedmail.update_proxy_bindingUpdate Proxy Binding
- proxiedmail.create_webhook_receiverCreate webhook receiver
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Proxiedmail in three steps.
- 01Your users connect ProxiedmailThey add their Proxiedmail api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create webhook receiver” can wait for the user to approve.
- 03Any agent can actYour agent calls Proxiedmail through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('proxiedmail', { read: 'allow', write: 'ask', // create_webhook_receiver destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Proxiedmail connects.
Users add their Proxiedmail 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 Proxiedmail 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 Proxiedmail from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Proxiedmail and Arc0, answered.
Can I use Proxiedmail with Claude, ChatGPT or Cursor?
Yes. Connect Proxiedmail 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 Proxiedmail actions you allow.
How do users connect Proxiedmail?
Users add their Proxiedmail 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 Proxiedmail actions can my agent take?
5 in total: 3 read, 2 write and 0 destructive, such as “create webhook receiver”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Proxiedmail?
Yes. Allow read actions and deny writes in the Proxiedmail policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Proxiedmail too?
Yes. The same Proxiedmail connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Proxiedmail into your agent.
Your users connect Proxiedmail once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan