Optical Context MCP for Claude Code

io.github.chrboebel/optical-context-mcp

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

client:Claude Code transport:stdio runtime:pypi

Install Optical Context MCP in Claude Code

run in your project directory

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

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs