# Content Core

> Use this tool when you need to extract intelligent content from diverse media sources, such as URLs, documents, videos, audio files, and images, to automate research, analyze content, or build AI agents. Content Core provides a unified interface for multiple extraction engines, handling complex workflows like transcript extraction and OCR. It is ideal for use cases requiring automated processing of mixed media content without manual preprocessing.

Canonical page: https://skillsregistry.net/skills/content-core  
JSON: https://api.skillsregistry.net/v1/skills/content-core

## Description

Content Core MCP Server provides intelligent content extraction from diverse media sources including URLs, documents (PDF, Office files, EPUB), videos, audio files, and images through a unified interface. Built by Luis Novo, it leverages multiple extraction engines with smart auto-detection - using Docling for documents when available, falling back to PyMuPDF, and supporting Firecrawl, Jina, or BeautifulSoup for web content based on API availability. The server handles complex workflows like YouTube transcript extraction, audio/video transcription via OpenAI Whisper, and OCR for images, making it valuable for research automation, content analysis, and building AI agents that need to process mixed media content without manual preprocessing.

## Trust

- **Trust score (0–1):** 0.35
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/content-core)
- **Repository:** <https://github.com/lfnovo/content-core>

## 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": "content-core"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/content-core` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/content-core/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