PDF SPEC MCP Server

@shuji-bonji

リポジトリ

基本情報

カテゴリ

ファイルとストレージ

トランスポート

stdio

作者

shuji-bonji

投稿者

shuji narumi

PDF SPEC MCP Server について

About

#pdf#pdf-specification#map-server

PDF SPEC MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "pdf-spec": {
      "command": "npx",
      "args": [
        "-y",
        "@shuji-bonji/pdf-spec-mcp"
      ],
      "env": {
        "PDF_SPEC_DIR": "/path/to/pdf-specs"
      }
    }
  }
}

PDF SPEC MCP Server のツール

List all discovered PDF specifications with metadata

Get section hierarchy (table of contents) with configurable depth

Get structured content of a specific section

Full-text keyword search across a specification

Extract normative requirements (shall/must/may)

Lookup term definitions

Extract table structures from a section

Compare PDF 1.7 and PDF 2.0 section structures

概要

What is PDF SPEC MCP Server?

An MCP (Model Context Protocol) server that provides structured access to ISO 32000 (PDF) specification documents. It enables LLMs to navigate, search, and analyze PDF specifications through well-defined tools. Users must obtain the PDF specification files separately from sources like the PDF Association.

How to use PDF SPEC MCP Server?

Install the npm package, set the PDF_SPEC_DIR environment variable to the directory containing your PDF specification files, then run with npx or configure in an MCP client (e.g., Claude Desktop, Cursor). All tools accept an optional spec parameter (default: iso32000-2).

Key features of PDF SPEC MCP Server

Multi-spec support for up to 17 PDF-related documents
Structured content extraction (headings, paragraphs, lists, tables, notes)
Full-text search with section-aware context snippets
Normative requirements extraction (shall/must/may)
Definitions lookup from Section 3
Multi-page table extraction with header merging
Version comparison between PDF 1.7 and PDF 2.0

Use cases of PDF SPEC MCP Server

Navigating and querying PDF 2.0, PDF/UA, or technical specifications (TS)
Extracting specific section content for LLM-based analysis
Searching for keywords across specifications with contextual results
Comparing section structures between PDF 1.7 and PDF 2.0
Retrieving normative requirements or term definitions for compliance checks

よくある質問

Do I need to download the PDF specification files separately?

Yes. PDF specification files are copyrighted and are **not included** in the package. They must be obtained from sources like the [PDF Association](https://pdfa.org/sponsored-standards/) and placed in a local directory.

What environment variable is required?

The `PDF_SPEC_DIR` environment variable (pointing to the directory containing the PDF specs) is required; there is no default.

Can I use only a subset of the supported specifications?

Yes. Place only the specification files you need. At minimum, ISO 32000-2 (PDF 2.0) is recommended.

What transport does the server use?

The server communicates over stdio using JSON-RPC, as shown in the architecture diagram.

What tools does the server expose?

The server provides eight tools: `list_specs`, `get_structure`, `get_section`, `search_spec`, `get_requirements`, `get_definitions`, `get_tables`, and `compare_versions`.

「ファイルとストレージ」の他のコンテンツ

drop.media

Upload once. Find, use and share across your AI workflows. drop.media is one media library for you and every AI agent you use: files added from Claude, ChatGPT, Cursor, the terminal or the web can be found, reused and sh