Optical Context MCP for Zed

io.github.chrboebel/optical-context-mcp

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

client:Zed transport:stdio runtime:pypi

Install Optical Context MCP in Zed

~/.config/zed/settings.json · windows: %APPDATA%\Zed\settings.json

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

Merge this into your existing settings object — do not replace the file. Zed docs