agentmods.dev

pdf-mcp

pdf-mcp is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from jztan/pdf-mcp. Its token cost is not measured, scanned A, original, MIT.

A local tool for searching and extracting information from PDF files. It supports text, tables, images, contents pages, scanned documents, and languages such as Chinese, Japanese, and Korean.

In plain words
What is it for?
Use it to search PDFs by keywords or meaning, extract structured content, run OCR on scans, and reuse results from a local cache.
Why use it?
It helps an agent find relevant PDF content and work with scanned or complex documents without manually reading every page.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 133repo +3 yesterday A scan Socket: warn tokens not measured original MIT

Good fit Use it to search PDFs by keywords or meaning, extract structured content, run OCR on scans, and reuse results from a local cache.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/jztan/pdf-mcp/pdf-mcp
View source ↗ jztan/pdf-mcp pdf-mcp.jztan.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/jztan/pdf-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pdf-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/jztan/pdf-mcp/pdf-mcp/github.svg)](https://agentmods.dev/mcp/jztan/pdf-mcp/pdf-mcp)
Your own site
<a href="https://agentmods.dev/mcp/jztan/pdf-mcp/pdf-mcp"><img src="https://agentmods.dev/badge/mcp/jztan/pdf-mcp/pdf-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pdf-mcp

Your own site · 80×15
<a href="https://agentmods.dev/mcp/jztan/pdf-mcp/pdf-mcp"><img src="https://agentmods.dev/badge/mcp/jztan/pdf-mcp/pdf-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits How audits are shown
Origin original No closer match found in the catalogue.
Security

Grade A, and why

pdf-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 12 lines

What it actually says

{
  "pdf-mcp": {
    "command": "uvx",
    "args": [
      "pdf-mcp"
    ],
    "env": {
      "PDF_MCP_CACHE_DIR": "",
      "PDF_MCP_CACHE_TTL": ""
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 12 lines scan A 69a5b274d188

Subscribe to this mod's changes

pdf-mcp is an MCP server published in the GitHub repository jztan/pdf-mcp (133 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DocumentsLLMPDFaiclaudedocument-processingmcp
Related

Other mcp servers, from other repositories

nutrient-dws-mcp-server

Nutrient Processor + Data Extraction MCP: convert, OCR, sign, redact, and extract PDFs/Office docs. Runs locally from the @nutrient-sdk/dws-mcp-server npm package. Needs 5 environment variables to run.

PSPDFKit/nutrient-dws-mcp-server · not measured

pdf-rag-mcp

MCP server "pdf-rag-mcp" as configured in MBaranekTech/pdf-rag-mcp. Runs locally from the pdf-rag-mcp Python package.

MBaranekTech/pdf-rag-mcp · not measured

pdfmux

Self-healing PDF extraction for RAG — #2 of 8 engines on opendataloader-bench (0.903). Flags pages it can't read instead of dropping them, and certifies any extractor's output for silent drops. Verify signed manifests offline, free. Per-page confidence, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse…

NameetP/pdfmux · not measured

paper-intelligence

MCP server enabling AI agents to efficiently search and understand PDF documents. Runs locally from the paper-intelligence Python package.

Strand-AI/paper-intelligence · not measured

pdf-suite-mcp

37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key. Runs locally from the pdf-suite-mcp npm package.

beepboop2025/pdf-suite-mcp · not measured

pdf-toolkit-mcp

Legacy PDF Toolkit identity, pinned to its 2.1.1 package; maintained successor: PDF Suite MCP. Runs locally from the pdf-suite-mcp npm package.

beepboop2025/pdf-suite-mcp · not measured