pdf-mcp — security grade SAFE, quality 81/100

Security audit verdict: SAFE · quality 81/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by jztan · MCP Server · ★ 136

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is pdf-mcp safe to install? View the security audit →

About pdf-mcp

pdf-mcp Surgical PDF access for AI agents — search, read, and extract without flooding context. A Model Context Protocol (MCP) server that enables AI agents to read, search, and extract content from PDF files. Built with Python and PyMuPDF, with SQLite-based caching for persistence across server restarts. mcp-name: io.github.jztan/pdf-mcp Try it in your browser See what your AI agent sees → Drop in any PDF and watch an agent skim it, search it, and read only the pages that matter — using a fraction of the tokens. 100% client-side, no install required. [<img src="https://raw.githubusercontent.com/jztan/pdf-mcp/develop/docs/images/demo.gif" alt="pdf-mcp browser de

agentic-ragaicjkclaudeclaude-codecodex-clidocument-processingllmmcpmcp-server

Quick Facts

Stars136
Forks14
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score81.3392335563874/100
Open Issues1
Last Updated2026-09-22
Created2026-01-28
Platformsclaude-code, cli, codex, mcp, python
Est. Tokens~17k

pdf-mcp alternative? Top 6 similar tools

Looking for a pdf-mcp alternative? If you're comparing pdf-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pdfmux by NameetP · ⭐ 82

    PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently

  • roampal-core by roampal-ai · ⭐ 50

    Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo

  • octocode by Muvon · ⭐ 475

    Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o

  • claude-historian-mcp by Vvkmnn · ⭐ 178

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • youtube-connector-mcp by ShellyDeng08 · ⭐ 71

    MCP server for YouTube — search videos, get transcripts, channels, and playlists. Works with Claude, Cursor &

  • nutrient-dws-mcp-server by PSPDFKit · ⭐ 69

    A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (D

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is pdf-mcp?

pdf-mcp is MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: agentic RAG with hybrid semantic + keyword search, selective page reads, tables, images, OC. It is categorized as a MCP Server with 136 GitHub stars.

What programming language is pdf-mcp written in?

pdf-mcp is primarily written in Python. It covers topics such as agentic-rag, ai, cjk.

How do I install or use pdf-mcp?

You can find installation instructions and usage details in the pdf-mcp GitHub repository at github.com/jztan/pdf-mcp. The project has 136 stars and 14 forks, indicating an active community.

What license does pdf-mcp use?

pdf-mcp is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to pdf-mcp?

The top alternatives to pdf-mcp on Agent Skills Hub include pdfmux, roampal-core, octocode. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools