Content Core

Data and operations teams that need text pulled out of mixed sources such as documents, web pages and recordings.

Use it now Want it running at your company?

Recommendedour rating
173gitHub stars
MITlicence
7 days agolast update

Use it now

claude mcp add content-core -e OPENAI_API_KEY=sk-... -- uvx content-core mcp

Install in Cursor Install in VS Code Open the original ↗

Third party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.

README.md

Loading the file...

What it does

Extracts content from web pages, PDFs, Word documents, YouTube transcripts, audio and video. It picks the extraction engine automatically and returns structured JSON. You can use it as a Python API, a command line tool or an MCP server.

Use cases

01Extract text from a folder of PDFs
02Get the transcript of a YouTube video
03Turn a web page into structured JSON

Questions about
Content Core.

What is Content Core used for?

Data and operations teams that need text pulled out of mixed sources such as documents, web pages and recordings. Extracts content from web pages, PDFs, Word documents, YouTube transcripts, audio and video. It picks the extraction engine automatically and returns structured JSON. You can use it as a Python API, a command line tool or an MCP server.

How do I install Content Core?

Run this in your terminal: claude mcp add content-core -e OPENAI_API_KEY=sk-... -- uvx content-core mcp

Is Content Core open source?

Yes. The code is on GitHub (lfnovo/content-core) under the MIT licence.

Is Content Core safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.

Related resources

Read the guide: AI data analysts: ask your data ↗