PDF Spec (PDF Agent Stack)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/shuji-bonji-pdf-spec-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

8 read · 0 write · 0 deleteRead-only

Secrets

None asked for

Install scripts

None found

Runs as

Node.js package

Tools (8)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• compare_versionsCompare PDF 1.7 and PDF 2.0read-only

  Compare sections between PDF 1.7 (ISO 32000-1) and PDF 2.0 (ISO 32000-2). Returns matched sections (same or moved), added sections (new in 2.0), and removed sections (absent in 2.0). Uses title-based automatic matching.

• get_definitionsGet term definitionsread-only

  Get term definitions from the "Terms and definitions" clause of the PDF specification (clause 3 of ISO 32000-2, clause 4 of ISO 32000-1 / pdf17). Returns structured definitions with term, definition text, notes, and sources.

• get_requirementsExtract normative requirementsread-only

  Reads the STANDARD, not your file. Extract normative requirements (shall/must/may) from the PDF specification (ISO 32000-2). Returns structured requirements with the sentence context, section, and requirement level. It tells you what the specification requires, never whether a given PDF satisfies it — to check a file, use pdf-verify-mcp (validate_conformance / evaluate_policy).

• get_sectionGet section contentread-only

  Get the content of a specific section from the PDF specification (ISO 32000-2). Returns structured content including headings, paragraphs, lists, tables, and notes. A parent section returns its entire subtree (all subsections, in document order); top-level clauses can therefore return very large responses — prefer the most specific section number you know.

• get_structureGet section hierarchyread-only

  Get the section hierarchy of the PDF specification (ISO 32000-2). Returns the table of contents with section numbers, titles, and page numbers.

• get_tablesExtract tablesread-only

  Extract table structures from a specified section of the PDF specification (ISO 32000-2). Returns tables with headers, rows, and optional captions. A parent section returns the tables of its entire subtree (all subsections).

• list_specsList available specificationsread-only

  List all available PDF specification documents. Returns document IDs, titles, page counts, and categories, plus `coverage.gaps` — the normative areas this corpus does NOT contain (PDF/A, PAdES). Read the gaps before concluding that a requirement does not exist. Use the returned IDs as the `spec` parameter in other tools.

• search_specSearch the specificationread-only

  Search the PDF specification (ISO 32000-2) for a keyword or phrase. Returns matching sections with context snippets. The first call may take a few seconds to build the search index; it is then cached on disk, so later processes start warm. No hits means "this corpus cannot answer", NOT "no such requirement exists" — ISO 19005 (PDF/A) and ETSI PAdES are outside it (see list_specs -> coverage.gaps).

Signals

Stars

2

Forks

0

Open issues

1

Last commit

Oct 21, 2026 (7 days ago)

Last release

Oct 21, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.shuji-bonji/pdf-spec-mcp

Version

0.9.0

Auth

No auth

Packages

npm @shuji-bonji/pdf-spec-mcp

License

MIT

Repository

github.com/shuji-bonji/pdf-spec-mcp

Website

shuji-bonji.github.io/pdf-agent-stack/

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql