← 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

    Agents

    Give any AI coding agent the ability to solve captchas with NoCaptchaAI.

    Loading…

    PreviousGoNextModel Context Protocol (MCP)
    [ ] Docs[ ] Extension[ ] Pricing[ ] Changelog[ ] Partners[ ] Terms[ ] Privacy[ ] Cookies[ ] Refunds[ ] Contact

    Spicrawl

    Free web scraping API for AI agents.

    spicrawl.com

    Spicrawl

    © 2026 NoCaptchaAI

    AI coding agents — Claude Code, OpenAI Codex, Cursor, Cline, and others — frequently hit captcha walls while browsing, scraping, or automating the web. NoCaptchaAI lets you hand that capability to the agent so it can clear the challenge and keep going.

    There are two ways to wire it up:

    • Call the API directly. Any agent that can make HTTP requests can POST /createTask and poll POST /getTaskResult against https://api.nocaptchaai.com. This works everywhere but the agent has to know the request shape each time.
    • Use an MCP server (recommended). A Model Context Protocol server wraps those endpoints as first-class tools (create_task, get_task_result, solve, balance). The agent then sees "solve this captcha" as a native action, with typed inputs and outputs, instead of hand-rolling HTTP calls.

    Every integration below builds on one of these two foundations. Start with the MCP page — it is the source of truth for the server config the agent pages reuse.

    Model Context Protocol (MCP)The foundational server that exposes solving as agent tools. Read this first.Claude CodeAdd the MCP server with claude mcp add, then ask Claude Code to solve.OpenAI CodexRegister the MCP server in ~/.codex/config.toml.CursorAdd the MCP server via .cursor/mcp.json and use it in Composer.ClineAdd the MCP server in Cline's MCP settings.OpenClawWire up MCP or call the API directly from an autonomous browser agent.

    More integrations on the way

    This list keeps growing. Every agent we support — and any agent you bring yourself — builds on the same MCP server or the raw API. Once you understand those two, adding a new agent is just a config snippet.

    Grab an API key from the dashboard before you start.