Twocaptcha for AI agents
2Captcha solves CAPTCHAs programmatically, used by developers whose automated workflows occasionally need a CAPTCHA cleared to continue. 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 Twocaptcha.
Submit a CAPTCHA to be solved
Send a CAPTCHA image or task and get back the solved answer.
Check account balance
Read the remaining account balance as a read-only check before a large batch of requests.
Report an incorrect solve
Flag a CAPTCHA that was solved incorrectly so it can be credited back.
5 Twocaptcha actions, graded by risk.
Every Twocaptcha action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- twocaptcha.get_balanceGet Account Balance
- twocaptcha.test_requestTest Request Parameters
write
3Create and change things. Allow, or ask the user first.
- twocaptcha.create_taskCreate CAPTCHA Task
- twocaptcha.report_incorrectReport Incorrect CAPTCHA
- twocaptcha.report_incorrect_image_captchaReport Incorrect Image Captcha
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Twocaptcha in three steps.
- 01Your users connect TwocaptchaThey add their Twocaptcha api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create CAPTCHA Task” can wait for the user to approve.
- 03Any agent can actYour agent calls Twocaptcha through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('twocaptcha', { read: 'allow', write: 'ask', // create_task destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Twocaptcha connects.
Users add their Twocaptcha 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 Twocaptcha 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 Twocaptcha from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Twocaptcha and Arc0, answered.
Can I use Twocaptcha with Claude, ChatGPT or Cursor?
Yes. Connect Twocaptcha 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 Twocaptcha actions you allow.
How do users connect Twocaptcha?
Users add their Twocaptcha 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 Twocaptcha actions can my agent take?
5 in total: 2 read, 3 write and 0 destructive, such as “create CAPTCHA Task”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Twocaptcha?
Yes. Allow read actions and deny writes in the Twocaptcha policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Twocaptcha too?
Yes. The same Twocaptcha connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Twocaptcha into your agent.
Your users connect Twocaptcha 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