Comprehensive API documentation, integration guides, and code examples for CapMonster Cloud AI CAPTCHA solver.
Welcome to the official documentation repository for CapMonster Cloud — the high-speed AI-powered CAPTCHA solving infrastructure for developers and automation engineers.
Here you will find full API specifications, payload samples, and step-by-step guides for bypassing Cloudflare Turnstile, reCAPTCHA v2/v3/Enterprise, DataDome, GeeTest, and Amazon WAF.
👉 Get your Free API Key & Free Trial Balance on CapMonster Cloud
Explore our live hosted documentation portal:
| Section | Description | Live Link |
|---|---|---|
| 🚀 Getting Started | Quickstart tutorial, account setup, and balance activation | Read Guide |
| 🧩 CAPTCHA Task Types | reCAPTCHA, Turnstile, GeeTest, DataDome, and WAF specs | View Tasks |
| ⚙️ API Methods | createTask, getTaskResult, getBalance reference |
API Reference |
| 🌐 Browser Extensions | Chrome and Firefox automatic captcha solving guides | Extension Docs |
Accelerate your automation pipeline with our official client libraries and integrations:
- 🐍 Python SDK — Async, Playwright, Selenium, and Requests.
- 🟢 Node.js / JavaScript SDK — Official Node.js library with TypeScript support.
- 🔷 .NET / C# SDK — Official .NET package for C# automation projects.
- 🧩 n8n Community Node — No-code workflow automation node.
- 🤖 MCP Server — Connect AI agents (Claude, Cursor, etc.) directly to CapMonster Cloud via Model Context Protocol.
- 🎭 MCP Server for Patchright — Stealth browser automation with built-in captcha solving for AI agents.
- 📦 All Repositories & SDKs — Full list of open-source tools.
This documentation portal is built with Docusaurus 3. Follow the instructions below to preview or contribute to the documentation locally.
Install the project dependencies using Yarn or npm:
yarn install
# or
npm installStart a local development server with live reload:
# Start English docs (default)
yarn start
# Start Russian docs
yarn start -- --locale ruGenerate static content into the build directory:
yarn build
yarn serve- Russian documentation: located in the
/docsdirectory. - English documentation: located in
/i18n/en/docusaurus-plugin-content-docs/current/.
When adding a new article, create the corresponding markdown file in both directories with identical filenames and category paths.
The live site is built and published by Cloudflare Pages (project capmonstercloud-docs-v2) directly from this GitHub repository. Every push to master triggers a production build. There is no deploy step in this repo — merging to master is the deploy.
The Cloudflare build runs npm run build, which is:
node scripts/generate-llms.mjs— generates the plain-text documentation for AI agents (see below);docusaurus build— builds the site intobuild/.
Search (Algolia) credentials are provided as environment variables in the Cloudflare Pages project settings. Never commit them to this repository — it is public.
The Dockerfile is a legacy artifact from a previous hosting setup and is not used by the current deployment.
Alongside the HTML pages the build publishes plain-text copies of the documentation, used by the CapMonster Cloud MCP server and other AI agents:
https://docs.capmonster.cloud/llms.txt— index of all pages with short descriptions;https://docs.capmonster.cloud/llms-full.txt— the whole documentation in one file;https://docs.capmonster.cloud/docs/<page>.txt— one file per page, e.g./docs/captchas/recaptcha-v3-task/→/docs/captchas/recaptcha-v3-task.txt.
They are generated from the English MDX sources on every build by scripts/generate-llms.mjs (output is git-ignored), so they are always in sync with the deployed pages. Content that lives in React components rather than MDX (<McpNotice/>, <PriceBlock/>, <BlogLink/>) is rendered to text by that script — if you add a new content-bearing component, teach the script about it too.
To check locally:
npm run build # generates txt files + builds the site
npm run verify-llms # checks that txt files exist and match the built pagesThe same check runs in GitHub Actions (.github/workflows/llms-txt.yml) on every pull request.