Extract text and images from PDFs with automatic fallback to vision mode when text is corrupted or unreadable. Built for developers integrating PDFs into LLM pipelines.
io.github.PyJudge/pdf4vllm
Local install
STDIO
No auth required
How models use it and what it is built for.
Extract text and images from PDFs with automatic fallback to vision mode when text is corrupted or unreadable. Built for developers integrating PDFs into LLM pipelines.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Pyjudge Pdf4vllm.
Paste any of these into Agent Studio after connecting Pyjudge Pdf4vllm.
Common questions about connecting and running Pyjudge Pdf4vllm.
How does pdf4vllm detect text corruption?
The server auto-detects text corruption in PDFs and automatically switches to image mode when text is unreadable or corrupted. The exact detection algorithm is not detailed in the registry, so check the project repository for implementation specifics.
What's the difference between text mode and image mode?
Text mode extracts readable text from PDFs; image mode converts PDF pages to images for processing by vision LLMs. The server automatically chooses the best mode based on whether text corruption is detected.
How do I install and run pdf4vllm-mcp?
Install via `uvx pdf4vllm-mcp@1.0.2`. The server runs over stdio transport, so it integrates directly with MCP-compatible clients and LLM applications.
Can I force text mode or image mode, or is it always automatic?
The registry indicates auto-detection is the default behavior. For control over mode selection, check the project documentation or GitHub repository for configuration options.
What file formats does pdf4vllm support?
The server is designed for PDF processing. For support of other formats or detailed format specifications, refer to the project repository.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams