# ddddocr CAPTCHA Recognition

> Use this tool when you need to automate the solving of various CAPTCHA types, such as text-based verification codes, object detection challenges, and slider puzzles, to support web scraping automation, testing workflows, and accessibility tools. It takes base64-encoded images or file paths as input and provides solved CAPTCHA outputs through a TypeScript MCP interface. Ideal for use cases where programmatic solving of visual verification challenges is required, enabling seamless automation of workflows that involve CAPTCHA verification.

Canonical page: https://skillsregistry.net/skills/ymeng98-ddddocr-captcha  
JSON: https://api.skillsregistry.net/v1/skills/ymeng98-ddddocr-captcha

## Description

A CAPTCHA recognition server built by ymeng98 that integrates the ddddocr Python library for automated solving of various CAPTCHA types through a TypeScript MCP interface. The implementation provides tools for OCR text recognition, object detection in image-based CAPTCHAs, slider puzzle matching, and health monitoring, using a hybrid architecture where TypeScript handles MCP communication while spawning Python processes to execute ddddocr operations on base64-encoded images or file paths. It supports multiple CAPTCHA formats including text-based verification codes, click-to-select object challenges, and sliding puzzle verification, making it useful for web scraping automation, testing workflows, and accessibility tools that need to programmatically solve visual verification challenges.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ymeng98-ddddocr-captcha)
- **Repository:** <https://github.com/ymeng98/ddddocr-captcha-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ymeng98-ddddocr-captcha"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ymeng98-ddddocr-captcha` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ymeng98-ddddocr-captcha/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt