← nocaptchaai.comDocs
    DocsChangelog

    Get Started

    Start Here
    QuickstartAuthenticationError Codes
    Browser Extension

    Captcha Types

    Token Tasks
    Cloudflare Turnstile Task
    Image Tasks
    ReCaptcha v2GeeTest V4ImageToTextBLS CaptchaBinanceAWS WAFTikTokDB-betMTCaptchaTencentProSOPO

    API Reference

    Overview
    Solver
    Create async captcha solving taskPoll task result (GET)Poll task resultSolve captchaGet response statusCollect endpoint (reserved)Report accuracy feedbackGet accuracy report
    Balance
    Check balance & plan infoLegacy balance formatList all error codes
    System
    Health check

    SDKs

    OverviewPythonJavaScript / Node.jsGo

    Agents

    OverviewModel Context Protocol (MCP)Claude CodeOpenAI CodexCursorClineOpenClaw

    Guides

    Browser ExtensionError HandlingChoosing a Task Type
    ← nocaptchaai.com
    Get API key
    Sign inGet API key

    OpenClaw

    Give an autonomous browser agent captcha-solving via MCP or the raw API.

    Loading…

    PreviousClineNextBrowser Extension
    [ ] Docs[ ] Extension[ ] Pricing[ ] Changelog[ ] Partners[ ] Terms[ ] Privacy[ ] Cookies[ ] Refunds[ ] Contact

    Spicrawl

    Free web scraping API for AI agents.

    spicrawl.com

    Spicrawl

    © 2026 NoCaptchaAI

    OpenClaw is an autonomous, browser-driving agent. Like any agent that can call external tools or HTTP APIs, it can clear captchas with NoCaptchaAI in one of two ways: through the MCP server if your build supports MCP, or by calling the API endpoints directly.

    Option A — MCP server

    If your OpenClaw version speaks MCP, register the NoCaptchaAI MCP server with the standard mcpServers config wherever OpenClaw reads its tool configuration:

    json
    {
      "mcpServers": {
        "nocaptchaai": {
          "command": "npx",
          "args": ["-y", "nocaptchaai-mcp"],
          "env": {
            "NOCAPTCHAAI_API_KEY": "your_key"
          }
        }
      }
    }
    

    The agent then has a solve_captcha tool and can call it whenever it hits a challenge.

    Option B — call the API directly

    If MCP isn't available, instruct the agent to call the endpoints itself. The flow is: POST /createTask to submit the challenge, then poll POST /getTaskResult until status is ready:

    bash
    # 1. Create the task
    curl -s https://api.nocaptchaai.com/createTask \
      -H "Content-Type: application/json" \
      -d '{
        "clientKey": "your_key",
        "task": {
          "type": "AntiTurnstileTask",
          "websiteURL": "https://example.com",
          "websiteKey": "0x4AAAAAAA..."
        }
      }'
    # -> { "taskId": "..." }
    
    # 2. Poll until status is "ready"; the token is in "solution"
    curl -s https://api.nocaptchaai.com/getTaskResult \
      -H "Content-Type: application/json" \
      -d '{ "clientKey": "your_key", "taskId": "..." }'
    

    Get your_key from the dashboard.

    Setup depends on your OpenClaw version

    OpenClaw's tooling and config layout vary between versions. Use whichever path your build supports — MCP if available, otherwise the raw API. Both hit the same endpoints behind the scenes.

    See the MCP page for the server config and reference implementation.