Optical Context MCP Server: Install & Setup

Install Optical Context in Claude Code

Claude Code

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

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "optical-context": {
      "command": "uvx",
      "args": [
        "optical-context-mcp"
      ]
    }
  }
}

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

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

Run: claude mcp add optical-context -- uvx optical-context-mcp

DigitalBrewLLC/playbykey-dev-tools

Chords, scales, progressions, transposition, and MIDI tools for music theory AI agents.

GermaniU/mineru-mcp

Parse PDF, DOCX, PPTX, XLSX and images to Markdown (tables, LaTeX) via a self-hosted MinerU API.

popnow-ai/popnow-mcp

AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling.

Ynewtime/markitai

Convert documents, images and web pages to clean Markdown, for agents: single, URL and batch tools.

Nishkalkashyap/printgo

Print PDFs, images, text, Markdown and HTML to your local printers, and track or cancel the jobs.

OrihuelaConde/local-whisper-mcp

Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.