Skip to content

Instantly share code, notes, and snippets.

@davidmezzetti

davidmezzetti/text-extract-mcp.md

Last active April 16, 2025 13:32
Show Gist options
  • Save davidmezzetti/f9f81a17f87341de2ef6d96c9a4aa95f to your computer and use it in GitHub Desktop.
Save davidmezzetti/f9f81a17f87341de2ef6d96c9a4aa95f to your computer and use it in GitHub Desktop.
Download ZIP
Raw
text-extract-mcp.md

Text extraction MCP service

Extract text using txtai, docling, docker. Service available via Model Context Protocol (MCP).

/tmp/config/config.yml

# Enable MCP server
mcp: True

# Enable file uploads
upload: True

# Textractor pipeline
textractor:

Run via Docker

docker run -it -p 8000:8000 -v /tmp/config:/config -e CONFIG=/config/config.yml 
--entrypoint uvicorn neuml/txtai-cpu --host 0.0.0.0 txtai.api:app

Test the service.

npx @modelcontextprotocol/inspector node build/index.js

Enter http://localhost:8000 and now you have a text extraction service via MCP.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment