Pdf4vllm MCP server

by PyJudge·io.github.PyJudge/pdf4vllm·v1.0.2

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

B75/100grade B

What users say

No reviews yet

Safety scan

B75/100

Adoption

New

0 stars27 downloads/wk

Reviews

Nobody has reviewed Pdf4vllm yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

list_pdfs
Find all PDF files in a directory. Always prefer this over ls or find for PDF files. Returns name, path, pages, and size for each PDF. Use the returned 'path' directly with read_pdf.

scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it

no findings

Code scan16 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 262 days ago4/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 75/100; higher than 45% of 1,337 Media servers
Tools: 1; the typical Media server has 7
Tools that change things: 0%; typical: 4%. Fewer write tools means less an agent can break
Downloads a week: 27; more than 13% of 365 Media servers with a package

What its tools let an agent do: 1 read

claude mcp add pdf4vllm -- uvx pdf4vllm-mcp

Is Pdf4vllm MCP server safe?: Mostly: it is graded B (75/100). Read the Pdf4vllm safety report
How do I install Pdf4vllm?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Pdf4vllm need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Pdf4vllm maintained?: The last commit was 296 days ago (2026-01-12). The latest release is v1.0.2.
What can I use instead of Pdf4vllm?: Servers from other publishers that do the same job: Free the Tools MCP server, three.ws Vision MCP server and anymd MCP server.
How does Pdf4vllm compare with other Media MCP servers?: safety score 75/100 (higher than 45% of 1,337 Media servers); tools 1 (the typical Media server has 7); tools that change things 0% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.

Same job from other publishers: the closest match first, then the best rated.

Free the Tools
Local PDF, image, data and text tools for AI assistants. Files stay on your computer.
not reviewed
Growing
A
three.ws Vision
Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.
More from nirholas →
not reviewed
Established
A
anymd
Any file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.
not reviewed
Established
A
oJo — HTML to image and PDF
Fill an HTML template with JSON and get a hosted PDF or image link. Free previews, no key.
not reviewed
Growing
A
PopNow
AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling.
not reviewed
Growing
A