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.
npx skills add sandraschi/pdf-mcp --skill pdf-expertgit clone --depth 1 https://github.com/sandraschi/pdf-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/skills/sandraschi/pdf-mcp/pdf-expert)<a href="https://agentmods.dev/skills/sandraschi/pdf-mcp/pdf-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/pdf-mcp/pdf-expert/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/skills/sandraschi/pdf-mcp/pdf-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/pdf-mcp/pdf-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01380 |
| Opus 5.5 | $0.00000 | $0.00552 |
| Sonnet 5.5 | $0.00000 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
pdf-expert 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 20d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pdf-mcp — Skill
Overview
pdf-mcp is a full-stack, local-first PDF intelligence MCP server. It exposes 16
portmanteau tools (operation-selected) covering extraction, manipulation, annotation,
forms, conversion, validation, redaction, classification, deduplication, RAG, briefs, and
an agentic chaining tool. The only optional dependency is a local LLM (Ollama / LM Studio)
for chat, pdf_do, auto-fill, and summaries. Everything else works offline.
Audience routing
- Agent, exploratory task ("what's in this PDF?", "find the clause") → start read-only:
pdf_analyze→pdf_extract(metadata|outline|text)→pdf_rag(search). - Agent, chained multi-step task →
pdf_do(task=..., path=...)(needs a local LLM). - Agent, structured pipeline → drive the operations explicitly and inspect each
successbefore continuing. - Human at the webapp → Workbench (view/compare/one-off tools), Pipeline (batch + recipes), Chat (asks), Settings (LLM setup), Inbox (watch folder), Logs.
- Human scripting → the REST surface (
/api/jobs,/api/rag/search,/api/health).
Tool catalogue (all 16)
Read-only inspection:
pdf_analyze—scannedvs digital, per-page layout stats. Always run before extraction on an unknown file.pdf_extract— ops:text,images,tables,metadata,fonts,links,outline. Optional 1-indexedpagesrange.pdf_validate— ops:pdfa,structure,accessibility,integrity,compare.pdf_classify— document type (invoice, receipt, report, contract, form, resume, letter, …).refine=trueuses the LLM.pdf_dedupe— exact + near duplicates overpaths,threshold(default 0.85).pdf_rag— ops:chunk,index,search,similar,synthesize,list_documents,delete_index. Hits carrysource_file+page_num.
Write (returns a new path; original untouched):
pdf_manipulate— ops:merge,split,rotate,reorder,delete_pages,compress,encrypt,decrypt,optimize.pdf_annotate— ops:watermark,stamp,highlight,underline,header_footer,page_numbers,summary_box(LLM).pdf_convert— ops:to_markdown,to_images,to_html,from_html,from_markdown,from_images.pdf_forms— ops:list_fields,fill,flatten,export_data,auto_fill(LLM).pdf_redact— blackentermsand/orpii=true(email, phone, IBAN, card, SSN, IP).pdf_export— document brief asmarkdown/json, optional LLM summary.
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.
- 20d ago Changed · +29 lines fe66ecaf8aca
- 1mo ago First seen · 82 lines · 0 tokens per session scan A a874e7dca660
pdf-expert is a skill published in the GitHub repository sandraschi/pdf-mcp (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,380 tokens. 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 skills, from other repositories
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.
sn-da-non-spreadsheet-analysis
A skill for extracting and analysing content from Word files, PDFs, and PowerPoint presentations. It can work with text, tables, numbers, charts, formatting, and information across multiple documents.
Read, create, fill, and transform PDF files. Covers extracting text and tables, OCR of scanned pages, filling fillable and flat forms, and flattening, merging, splitting, rotating, stamping and encrypting. Use when a task takes a .pdf as input or must produce one.
mineru
An AI-Native skill for parsing PDF / Office / image files into clean Markdown with MinerU — a fast, zero-config document parser for AI agents. Works with NO token via the lightweight Agent API and auto-upgrades to the Standard API (token) for large files, batches, and DOCX/HTML/LaTeX export. Use when: (1) Converting…
A PDF document tool for extracting text, tables, and metadata, creating documents, changing pages, adding annotations, and handling forms. A PDF is a fixed-layout document file.