Optical Context MCP for Windsurf

io.github.chrboebel/optical-context-mcp

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

client:Windsurf transport:stdio runtime:pypi

Install Optical Context MCP in Windsurf

~/.codeium/windsurf/mcp_config.json · windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

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

Global only — Windsurf has no per-project MCP config. Refresh Cascade after saving. Windsurf docs