Smartproxy for AI agents
Smartproxy runs a large network of residential, datacenter, and mobile proxies, along with scraping APIs, for teams that collect data from across the web. 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 Smartproxy.
Check available endpoints by type
Get the endpoints available for a proxy type before an agent configures a scraping job to use them.
Generate a custom endpoint
Generate a custom endpoint for a specific location or session, scoped to one task rather than the whole account.
Remove a whitelisted IP
Delete an IP from the whitelist after confirming it's no longer in use, tightening access to the account.
6 Smartproxy actions, graded by risk.
Every Smartproxy 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.
- smartproxy.get_api_keyGet API Key
- smartproxy.get_endpoints_by_typeGet Endpoints By Type
- smartproxy.list_endpoints_and_portsList Endpoints and Ports
write
2Create and change things. Allow, or ask the user first.
- smartproxy.generate_custom_endpointsGenerate Custom Endpoints
- smartproxy.generate_backconnect_endpointsGenerate Back Connect Endpoints
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- smartproxy.delete_whitelisted_ipDelete Whitelisted IP
Smartproxy in three steps.
- 01Your users connect SmartproxyThey add their Smartproxy api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “generate Custom Endpoints” can wait for the user, and “delete Whitelisted IP” can be denied outright.
- 03Any agent can actYour agent calls Smartproxy through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('smartproxy', { read: 'allow', write: 'ask', // generate_custom_endpoints destructive: 'deny', // delete_whitelisted_ip }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Smartproxy connects.
Users add their Smartproxy 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 Smartproxy 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 Smartproxy from any agent.
More web data and scraping apps.
Smartproxy and Arc0, answered.
Can I use Smartproxy with Claude, ChatGPT or Cursor?
Yes. Connect Smartproxy 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 Smartproxy actions you allow.
How do users connect Smartproxy?
Users add their Smartproxy 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 Smartproxy actions can my agent take?
6 in total: 3 read, 2 write and 1 destructive, such as “generate Custom Endpoints”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Smartproxy?
Yes. Actions like “delete Whitelisted IP” 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 Smartproxy too?
Yes. The same Smartproxy connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Smartproxy into your agent.
Your users connect Smartproxy once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan