Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Productivity
  4. /
  5. PDF RAG MCP
Productivity
PR

PDF RAG MCP

by jztan

pdf-mcp is an MCP server that lets AI agents search one PDF or a folder of PDFs by keyword or meaning and read only the pages they need. It also extracts tables, charts and scanned text.

Plugin·Contact for pricing

Visit registry.modelcontextprotocol.io(opens in a new tab)

About PDF RAG MCP

Key features of PDF RAG MCP

  • Hybrid keyword and semantic search within a PDF or across a folder
  • Read specific pages or ranges, or a whole document with a byte cap
  • Table extraction and chart data as exact (x, y) tables
  • OCR for scanned pages via Tesseract
  • Correct reading order for multi-column and Japanese vertical layouts
  • SQLite cache that persists across restarts
  • Flags hidden or injected text as untrusted
  • Optional CUDA acceleration for warming large folders

Who PDF RAG MCP is for

  • Developers giving agents access to long PDFs
  • Claude Code and Claude Desktop users
  • Researchers and analysts working with report collections
  • Teams sharing a warm PDF corpus over HTTP

How to use PDF RAG MCP

  1. 1

    Step 1: In Claude Desktop, download the pdf-mcp.mcpb file and drop it onto Settings > Extensions, then click Install.

  2. 2

    Step 2: For Claude Code and other clients, install with uv tool install pdf-mcp or pipx install pdf-mcp (Python 3.11 or later).

  3. 3

    Step 3: Register it, for example with claude mcp add pdf-mcp -- pdf-mcp. Other clients are covered in the project's docs/clients.md.

  4. 4

    Step 4: Install Tesseract if you need OCR on scanned pages.

  5. 5

    Step 5: Ask your agent to read a PDF by path or a folder, for example which pages discuss supply chain risks.

PDF RAG MCP FAQ

Can it search a whole folder of PDFs?

Yes. pdf_corpus_warm, pdf_corpus_overview and pdf_corpus_search work across a folder and return document and page provenance.

Does it handle scanned PDFs?

Yes, through OCR with Tesseract, which is parallel across pages. Tesseract must be installed separately for the pip route.

Can it run remotely?

Yes. pdf-mcp-http serves the same tools over HTTP and requires an auth token or an allow list, otherwise it exits rather than serve an open endpoint.

How does it treat hidden or injected text in a PDF?

Text from a PDF is treated as untrusted content. pdf_info with content_trust=True reports hidden text a reader cannot see, and the read tools flag it per page without stripping anything.

Technical details

Requirements

  • An MCP-compatible client; provider credentials or runtime dependencies may be required.

Details

Pricing
Contact for pricingFree and open source under the MIT license. No paid plans are stated.
Type
Plugin
Platforms
  • API
  • CLI
  • MCP
Categories
ProductivityDataResearch
Added
Sep 17, 2026
JzPublisherjztan

Built from public sources

We put this page together from PDF RAG MCP’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with PDF RAG MCP.

Work at PDF RAG MCP? Claim the listing to manage it yourself.

Something wrong here?

More from jztan

View publisher
RMRedmine MCPjztan · Contact for pricingRedmine MCP Server connects AI assistants to a Redmine instance. It exposes projects, issues, time tracking, wiki pages and files as MCP tools.Business · Contact for pricing

Related tools

See more
Zotero MCP iconZotero MCP54yyyu · Contact for pricingZotero MCP connects a Zotero research library to AI assistants so they can search, read, annotate and add to it. It also ships a chat panel that runs inside Zotero.Productivity · Contact for pricingSMSage MCPl33tdawg · Contact for pricingSAGE is a governed memory layer for AI agents. Each memory is signed by an agent, admitted through a review step, limited by permissions and kept with an audit trail.Productivity · Contact for pricingStratify MCP iconStratify MCPAeon Labs · Contact for pricingStratify is an MCP-based backtester for NIFTY and SENSEX options. You describe a strategy in plain words to Claude, ChatGPT or Gemini and get a costed result and a shareable report.Finance · Contact for pricing