PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
io.github.PyJudge/pdf4vllm
https://github.com/PyJudge/pdf4vllm-mcp
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Where to find authoritative docs and source for pdf4vllm.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio