pdf-mcp is an open-source project built for developers building AI agents and users working with large PDF collections.

Does pdf-mcp have a free plan?

Yes — pdf-mcp is open source under the Open Source license and free to use.

What platforms does pdf-mcp run on?

pdf-mcp runs on the web and the command line. It can also be self-hosted.

Is pdf-mcp still active?

Unverified. pdf-mcp has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.

What are alternatives to pdf-mcp?

Similar projects tracked by PulseGate include pdf-mcp, pdf-agent-mcp, and pdfops-mcp.

Is pdf-mcp open source?

Yes — pdf-mcp is open source under the Open Source license.

Back to the index

pdf-mcp

Name: pdf-mcp
Author: jztan

github.comInfrastructure

pdf-mcp is a self-hosted Model Context Protocol server that lets Claude Code and other AI agents work with large PDFs and folders of PDFs. It provides hybrid semantic and keyword search, selective page reading, table and image extraction, OCR, chart data access, and support for multi-column and CJK layouts.

Open SourceWebCLISelf-hosted

Visit github.com

2alternatives

10features

2026since

Overview

10 features

In the RAG, search & retrieval space, pdf-mcp takes a focused approach. It focuses on helping AI agents search and analyze large PDF collections without overflowing their context windows. It is built as an open-source project for developers building AI agents and users working with large PDF collections. The project is open source (Open Source). It runs on the web and the command line, and it can be self-hosted.

It is developed by jztan. Key capabilities include semantic search, keyword search, and selective page reading. It exposes integrations via an MCP server.

Summary written by a language model from the project’s public pages.

Semantic search
Keyword search
Selective page reading
Table extraction
Image extraction
OCR support
Chart data extraction
Multi-column layouts
CJK layout support
Folder search

Built with & integrations

AI providers

anthropicmultiple

Connectors

MCP

Runs on

BrowserCLISelf-hosted

Trust & compliance

License

Open Source

Verified signals

HTTPSOpen SourceFree tier

Indexing history

What PulseGate has recorded for this listing

Indexed29 Aug · 03:06 UTC
io.github.jztan/pdf-mcp verified against its public source
Source: PulseGate · Open

Frequently asked questions about pdf-mcp

What does pdf-mcp do?: Pdf-mcp focuses on helping AI agents search and analyze large PDF collections without overflowing their context windows. It is catalogued under RAG, search & retrieval on PulseGate.
Who is pdf-mcp for?: pdf-mcp is an open-source project built for developers building AI agents and users working with large PDF collections.
Does pdf-mcp have a free plan?: Yes — pdf-mcp is open source under the Open Source license and free to use.
What platforms does pdf-mcp run on?: pdf-mcp runs on the web and the command line. It can also be self-hosted.
Is pdf-mcp still active?: Unverified. pdf-mcp has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
What are alternatives to pdf-mcp?: Similar projects tracked by PulseGate include pdf-mcp, pdf-agent-mcp, and pdfops-mcp.pdf-mcp pdf-agent-mcp pdfops-mcp
Who makes pdf-mcp?: pdf-mcp is developed by jztan.
Is pdf-mcp open source?: Yes — pdf-mcp is open source under the Open Source license.

At a glance

Pricing: Open Source
Platforms: CLI · Web
Languages: English
License: Open Source
First seen: 29 Aug 2026
Built for: developers building AI agents and users working with large PDF collections
Model: Open source
Solves: Helping AI agents search and analyze large PDF collections without overflowing their context windows.

Developer

jztan

Index record

Indexed: 29 Aug 2026
Lifecycle: Alive
First seen: Aug 2026
Last seen: 29 Aug 2026

Identity audit (13)

Slug: io-github-jztan-pdf-mcp-github-com
Lifecycle state recorded: 29 Aug 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 29 Aug 2026
Timeline basis: Indexed-at chronology (no inferred launch/funding milestones).
Name from: Written by a language model from the project's public pages.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model, checked against the page's own declaration.
Last updated: 29 Aug 2026
Canonical URL: https://github.com/jztan/pdf-mcp

Ship this? Send a correction — no account, and you get a link to follow it.

Similar projects

Closest matches by what these projects do