PDF MCP

Name: PDF MCP
Author: jztan

作者：jztan版本 3.7.0i★ –i在你的电脑上运行

注册名称io.github.jztan/pdf-mcp

安装

概览

作者提供的说明（英文原文）

Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 文档、表格与办公

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： PDF_MCP_CACHE_DIR, PDF_MCP_CACHE_TTL, PDF_MCP_CACHE_MAX_MB

你需要

PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

下载作者的 .mcpb 文件

链接指向作者自己的文件；我们不托管也不重新打包它。打开文件后，Claude Desktop 会进行安装。

在终端中运行这条命令

claude mcp add pdf --env PDF_MCP_CACHE_DIR=your-value --env PDF_MCP_CACHE_TTL=your-value --env PDF_MCP_CACHE_MAX_MB=your-value -- uvx pdf-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "pdf": {
      "command": "uvx",
      "args": [
        "pdf-mcp"
      ],
      "env": {
        "PDF_MCP_CACHE_DIR": "your-value",
        "PDF_MCP_CACHE_TTL": "your-value",
        "PDF_MCP_CACHE_MAX_MB": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "pdf": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pdf-mcp"
      ],
      "env": {
        "PDF_MCP_CACHE_DIR": "your-value",
        "PDF_MCP_CACHE_TTL": "your-value",
        "PDF_MCP_CACHE_MAX_MB": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

PDF_MCP_CACHE_DIR env
Directory for storing PDF cache (default: ~/.cache/pdf-mcp)
PDF_MCP_CACHE_TTL env
Optional time expiry in hours; unset keeps a document while its PDF exists
PDF_MCP_CACHE_MAX_MB env
Cache size cap in MB, least recently used evicted first (default: 2048; 0 = no cap)

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 jztan 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“文档、表格与办公”中的其他服务器比较i

星标数多于此分类中其他 3543 个服务器的 0%
发布到注册中心的时间比此分类中其他 3543 个服务器的 95% 更新
基础检查结果等于或优于此分类中其他 3543 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

PDF MCP 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（3.7.0）于昨天进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv), MCPB。

有什么可以替代它？

同一分类中有：Agent-Native Calendar, Excel MCP Server, MCP Server for Excel

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Agent-Native Calendar

作者：BuilderIO

Agent-Native Google Calendar - manage events, sync, and public booking

在云端运行★ 7,620MIT2个月前更新

安装

Excel MCP Server

作者：haris-musa

Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.

在你的电脑上运行★ 4,276MIT7天前更新

安装

MCP Server for Excel

作者：sbroenne

Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.

在你的电脑上运行★ 847MIT4天前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

pdf-mcp

Agentic RAG over your PDFs, one file or a whole folder, as a single MCP tool.

The agent decides when to search; pdf-mcp does the retrieval and hands back excerpts. It is an MCP server that lets Claude Code and other AI agents search one PDF or a whole folder by meaning or keyword, read only the pages that matter, and cleanly pull out tables, images, and scanned text, even from multi-column and Japanese layouts, with optional CUDA acceleration for warming large corpora.

mcp-name: io.github.jztan/pdf-mcp

Try it in your browser

[See what your AI agent sees →](https://pdf-mcp.jztan.com/)

Drop in any PDF, or a whole folder of them, and watch an agent triage the corpus, search across every document at once, and read only the pages that matter, using a fraction of the tokens. 100% client-side, no install required.

Why pdf-mcp?

	Without pdf-mcp	With pdf-mcp
Large PDFs	Context overflow	Read only the pages you need
Finding content	Load everything	Hybrid search: BM25 keyword + semantic
Folders of PDFs	One document at a time	Warm, triage, and search a whole folder
Warming a big folder	Minutes of CPU embedding	Length-sorted small-batch CPU encode; optional CUDA embedding, one to two orders of magnitude faster on an NVIDIA card
Tables and charts	Lost in raw text	Structured rows, and `(x, y)` data from vector charts
Multi-column and vertical layouts	Columns interleaved	Correct reading order, including Japanese tategaki
Scanned PDFs	No text at all	OCR via Tesseract, parallel across pages
Repeated access	Re-parse every time	SQLite cache that survives restarts
Hidden or injected text	Silently ingested	Flagged as untrusted, nothing stripped

Installation

Claude Desktop: nothing to install first

[Download pdf-mcp.mcpb](https://github.com/jztan/pdf-mcp/releases/latest/download/pdf-mcp.mcpb).
In Claude Desktop, open Settings > Extensions, drag the file onto that page, and click Install.
Ask Claude about a PDF by its location, for example "Use pdf-mcp to summarize C:\Users\me\Downloads\report.pdf", or about a whole folder.

The first start downloads pdf-mcp's components (about 250 MB) and can take a few minutes; later starts take seconds. OCR for scanned pages is included: the first scanned page downloads an English-only Tesseract (about 14 MB). Needs Windows 10 or later, or macOS 13 or later (14 on Apple Silicon), and works in Claude Desktop's Chat. Updating, uninstalling and other details are in docs/clients.md.

Claude Code and other MCP clients

Needs Python 3.11 to 3.14. On 3.15 the installer falls back to a very old release, because a dependency has no 3.15 build yet. Install the pdf-mcp command with uv or pipx:

uv tool install pdf-mcp     # or: pipx install pdf-mcp

pip install pdf-mcp works inside a virtual environment; Homebrew's Python and recent Debian and Ubuntu refuse a system-wide pip install.

Then add it to your client. For Claude Code:

claude mcp add pdf-mcp -- pdf-mcp

For VS Code, Cursor, Codex CLI, Kiro or any other MCP client, see [docs/clients.md](docs/clients.md). Then ask your agent to read a PDF.

Search, the corpus tools, tables and multi-column and CJK reading order work out of the box. For non-English documents, see language support. OCR on scanned pages also needs Tesseract:

brew install tesseract                             # macOS

sudo apt install tesseract-ocr # Ubuntu/Debian winget install -e --id UB-Mannheim.TesseractOCR # Windows

Optional: CUDA embedding on an NVIDIA card warms large folders one to two orders of magnitude faster; see docs/configuration.md.

From Python

pdf-mcp's tools are also plain Python functions, so you can import them and hand a PDF to the Anthropic SDK without running a server. Two runnable scripts, for a question and for a whole document: [examples/](examples/).

Why this exists, and what broke along the way: Claude's 100-page PDF limit and how I got around it

Tools

13 specialized tools rather than one monolithic one. Typical pattern: pdf_info to plan, pdf_search to locate (its paragraph excerpts often answer the question outright), pdf_read_pages when you need more. For a folder, pdf_corpus_overview to triage, then pdf_corpus_search.

Tool	What it does
`pdf_info`	Page count, metadata, TOC summary, scanned-page detection. Call first.
`pdf_search`	Hybrid search (keyword + semantic) by page or section; hits carry an excerpt, source coordinates, the enclosing outline section and a table's lead-in sentence
`pdf_read_pages`	Read specific pages or ranges, with OCR on demand, tables, and embedded images
`pdf_read_all`	Read a whole document in one call, byte-capped
`pdf_get_toc`	Full table of contents for documents with many bookmarks
`pdf_render_pages`	Render pages as PNG for vision models: diagrams, handwriting, scans
`pdf_extract_chart`	Chart data as exact `(x, y)` tables, read from plot geometry
`pdf_corpus_warm`	Warm a folder of PDFs into the cache within a time budget
`pdf_corpus_overview`	Per-document triage cards for a folder
`pdf_corpus_search`	Search across a folder; hits carry document and page provenance
`pdf_cache_stats`	Per-document cache breakdown and total size
`pdf_cache_clear`	Clear expired or all cache entries
`server_info`	Which optional features and config are active

Text returned by any of these is untrusted content extracted from a PDF. pdf_info(content_trust=True) reports hidden text a human reader cannot see, and the read tools flag it per page.

Example prompts:

"Read the PDF at /path/to/document.pdf"

"Which pages discuss supply chain risks?" "Find sections about the training process" "Show me what page 5 looks like" "OCR pages 3-5 of the scanned PDF"

Full reference, every parameter and response shape: [docs/tool-reference.md](docs/tool-reference.md). Embedding model selection: [docs/embedding-models.md](docs/embedding-models.md).

Example Workflow

For a large document (e.g., a 200-page annual report):

User: "Summarize the risk factors in this annual report"

Agent workflow:

pdf_info("report.pdf") → 200 pages, TOC shows "Risk Factors" on page 89

pdf_search("report.pdf", "risk factors") → Matches with structural paragraph excerpts: each excerpt is the bullet, paragraph, or heading that matched, not a fixed-width window. Often enough to answer directly.

If excerpts are sufficient → synthesize answer

If more context needed: pdf_read_pages("report.pdf", "89-95") → Full page text for deeper reading

Remote / HTTP transport

STDIO is the default and is what every example above uses. pdf-mcp-http serves the same tools over HTTP, for clients that cannot spawn a process (the Anthropic API MCP connector, claude.ai custom connectors) and for a warm corpus shared by several clients.

export PDF_MCP_AUTH_TOKEN="$(openssl rand -hex 32)"

pdf-mcp-http

Paths resolve on the server, so an HTTP agent reads what is already there: files under an allow-listed root, or a URL the server fetches. It cannot hand over a file from its own machine. It is single-tenant and fails closed: with no auth token and no [paths] allow list, the process exits rather than serving an open endpoint.

Docker images are published to GHCR for amd64 and arm64, with everything baked in, so every tool works on the first request:

./deploy.sh              # token, image, start, health-check

cp your.pdf documents/ # this folder is the server's /data/pdfs

Read [docs/remote-access.md](docs/remote-access.md) for the trust boundary and threat model before deploying, and [docs/configuration.md](docs/configuration.md#http-transport-setup) for setup, client config, and token rotation.

Configuration

pdf-mcp works out of the box. To restrict which paths and URL hosts the server may touch, tune cache and worker settings, or add your own content-trust phrases, see [docs/configuration.md](docs/configuration.md).

Roadmap

See ROADMAP.md for planned features and release history.

Contributing

Contributions are welcome. See [docs/contributing.md](docs/contributing.md) for setup, checks, the coherence eval harness, and quality-loop guidelines.

Contributors

Thank you to everyone who has helped improve this project through code, reviews, testing, and feature requests:

@Summer907 · @ebbsanchez · @VooDisss · @DerDennisOP · @deepdmk · @TheSOV · @janLo · @bbulkow · @HillsCloud · @phinnphace

Per-release contributor credits are listed in the Changelog.

Security

Found a vulnerability? See SECURITY.md for the threat model, reporting channel, and expected response timeline. Please do not open a public GitHub issue for unpatched security reports.

License

MIT. See LICENSE.

Blog posts

The story behind the releases. Building pdf-mcp keeps surprising me: benchmarks that go the wrong way, formats that break everything, features I had to remove. I write about that thinking in The Dispatch. Come along if that's your kind of thing.

Background, benchmarks, and design notes from building pdf-mcp:

Getting started

[How I Built pdf-mcp](https://blog.jztan.com/how-i-built-pdf-mcp-solving-claude-large-pdf-limitations/?utm_source=github&utm_medium=referral&utm_campaign=pdf-mcp&utm_content=list-how-i-built-pdf-mcp-solving-claude-large-pdf-limita

只显示了开头部分；其余内容请在仓库中阅读