Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/shuji-bonji/pdf-spec-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/shuji-bonji/pdf-spec-mcp/pdf-spec-mcp)<a href="https://agentmods.dev/plugins/shuji-bonji/pdf-spec-mcp/pdf-spec-mcp"><img src="https://agentmods.dev/badge/plugins/shuji-bonji/pdf-spec-mcp/pdf-spec-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/shuji-bonji/pdf-spec-mcp/pdf-spec-mcp"><img src="https://agentmods.dev/badge/plugins/shuji-bonji/pdf-spec-mcp/pdf-spec-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pdf-spec-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://raw.githubusercontent.com/anthropics/claude-code/main/.claude-plugin/plugin.schema.json",
"name": "pdf-spec-mcp",
"version": "0.10.0",
"description": "ISO 32000 (PDF 仕様) の構造化参照 MCP server(8 ツール)。条項検索・要求事項 (MUST/SHOULD) 抽出・定義取得・版間比較を提供。収録対象は ISO 32000-1/-2 を中心とする PDF 関連 17 文書で、PDF/A (ISO 19005) と PAdES (ETSI EN 319 142) は対象外(list_specs の coverage.gaps)。ISO 仕様 PDF は利用者が用意し PDF_SPEC_DIR で指定する。検索索引は初回構築後にディスクへキャッシュする(既定 ~/.cache/pdf-spec-mcp。PDF_SPEC_CACHE_DIR で変更、PDF_SPEC_CACHE=off で無効、--build-cache で事前構築)。**本サーバは条文の参照であって適合判定器ではありません** — PDF ファイルの検査や適合判定は行わず、それは pdf-verify-mcp の役割です。",
"author": {
"name": "shuji-bonji",
"email": "[email protected]",
"url": "https://github.com/shuji-bonji"
},
"homepage": "https://github.com/shuji-bonji/pdf-spec-mcp",
"repository": "https://github.com/shuji-bonji/pdf-spec-mcp",
"license": "MIT",
"keywords": [
"pdf",
"iso-32000",
"specification",
"mcp",
"mcp-server",
"requirements"
],
"mcpServers": {
"pdf-spec": {
"command": "npx",
"args": [
"-y",
"@shuji-bonji/pdf-spec-mcp@latest"
],
"env": {
"PDF_SPEC_DIR": "${PDF_SPEC_DIR}"
}
}
}
}
What it installs
The manifest is a name and a version. 6 skills, 6 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 489 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill openspec-apply-change A 53 tokens
- Skill openspec-sync-specs A 57 tokens
- Skill openspec-propose A 66 tokens
- Skill openspec-update-change A 95 tokens
- Skill openspec-explore A 67 tokens
- Skill openspec-archive-change A 50 tokens
- Command OPSX: Explore A 18 tokens
- Command OPSX: Archive A 13 tokens
- Command OPSX: Propose A 21 tokens
- Command OPSX: Apply A 15 tokens
- Command OPSX: Sync A 14 tokens
- Command OPSX: Update A 20 tokens
- MCP server pdf-spec-mcp A not measured
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed 39f7bcd9a1be
- 5d ago Changed ea5a8397ba7e
- 1mo ago First seen · 35 lines scan A 3a0fda5faff6
pdf-spec-mcp is a plugin published in the GitHub repository shuji-bonji/pdf-spec-mcp (2 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
ra-mcp-tools
Skills for using Riksarkivet MCP tools — HTR transcription, archive search, document browsing.
conversiontools
Convert 140+ file formats directly in Gemini CLI - documents, data (JSON, CSV, XML, Parquet), images, audio, video, e-books, OCR, AI extraction, text-to-speech, speech-to-text, subtitles (SRT, VTT, ASS), and more. Or build a custom converter from a plain-language description when no standard one fits.
kolmopdf
High-fidelity PDF to Markdown parsing, layout-preserving PDF translation, and Markdown→DOCX/HTML/PDF/LaTeX conversion. Handles formulas, tables, and multi-column layouts that the built-in Read tool struggles with.
pdf-reader-mcp
An MCP server for examining the internal structure of PDF files. It can extract text, images, and tables and inspect items such as signatures, fonts, annotations, and accessibility tags.
superdocs
Typebar (formerly SuperDocs), the document harness for your AI: edit, draft, search, summarize and export styled documents (.docx / PDF / HTML / Markdown / plain text) via the Typebar MCP server. Single install bundles 38 MCP tools, 4 user-invocable workflow prompts and a skill that auto-loads when document work is…
pennyocr
Read PDFs and images as Markdown or text with exact per-call costs and hard spend caps. Requires your PennyOCR API key.