io.github.ChrBoebel/optical-context-mcpmedia

Optical Context MCP

Verified · yesterday

Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.

Install

claude mcp add optical-context-mcp -- uvx optical-context-mcp

Our take

Genuinely novel niche: compresses long OCR-heavy PDFs into dense packed PNGs so a vision-capable agent can retrieve a whole manual's visual structure in a few images instead of hundreds of pages. Real implementation with tests, CI, and an unusually honest README that tells you when NOT to use it (clean text PDFs, tiny files). Budget for Mistral OCR API costs — that's the engine underneath, and it's not optional.

reviewed by hand · 2026-07-06

Something wrong or dead here? Report it

Verification record

last verified: yesterday
github stars: 1
last commit: 3 mo ago
archived: no
license: MIT
in registry since: 2026-03-08

github.com/ChrBoebel/optical-context-mcp