pulsemcp scanned Safe content atomic mcp-remote

ddddocr CAPTCHA Recognition

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.

Cognium trust score

64%

Tier

Scanned

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-01.

Scan details: Circle-IR · 2026-09-01 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: media
Source: PulseMCP
Repository: github.com/ymeng98/ddddocr-captcha-mcp
Author type: human
Last scanned: 2026-09-01
Updated: 2026-09-01

View source Find related skills

MCP

Resolve ddddocr CAPTCHA Recognition from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

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

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"