pdf4vllm for VS Code

io.github.pyjudge/pdf4vllm

PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.

client:VS Code transport:stdio runtime:pypi

Install pdf4vllm in VS Code

.vscode/mcp.json

{
  "servers": {
    "pdf4vllm": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pdf4vllm-mcp"
      ]
    }
  }
}

Requires agent mode. MCP: Open User Configuration puts the same block in every workspace. VS Code docs