@shuji-bonji/pdf-reader-mcp
npm
v0.15.0
Source verified
Published by shuji-bonji — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server for PDF structure analysis - read, inspect, and validate PDF internals
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 3 = 97. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`dist/services/page-renderer.js:64`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const module = (await import(specifier)); pdfiumLibrary = await module.PDFiumLibrary.init(); } catch {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/services/page-renderer.js
In the server's implementation (`dist/services/page-renderer.worker.mjs:49`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; const module_ = await import(specifier); const library = await module_.PDFiumLibrary.init(); const document_ = await l
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/services/page-renderer.worker.mjs
Each tool and what it can reach — statically extracted from the published source.
get_page_countingests untrusted inputread_urlingests untrusted inputcompare_structureno sensitive capabilityextract_structured_textno sensitive capabilityextract_tablesno sensitive capabilityget_metadatano sensitive capabilityinspect_annotationsno sensitive capabilityinspect_fontsno sensitive capabilityinspect_signaturesno sensitive capabilityinspect_structureno sensitive capabilityinspect_tagsno sensitive capabilitylocate_objectsno sensitive capabilityread_imagesno sensitive capabilityread_textno sensitive capabilityrender_pageno sensitive capabilitysearch_textno sensitive capabilitysummarizeno sensitive capabilityvalidate_metadatano sensitive capabilityvalidate_taggedno sensitive capabilityScan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.15.0 latest |
A 97/100 | 2 | 1.13.0 | 2026-09-07 |
v0.14.0 |
A 97/100 | 2 | 1.13.0 | 2026-08-31 |
v0.13.0 |
A 97/100 | 1 | 1.13.0 | 2026-08-30 |
v0.12.0 |
A 97/100 | 1 | 1.13.0 | 2026-08-27 |
v0.11.2 |
A 97/100 | 0 | 1.12.1 | 2026-08-23 |
v0.11.1 |
A 97/100 | 0 | 1.12.1 | 2026-08-13 |
v0.10.0 |
A 97/100 | 0 | 1.10.0 | 2026-07-27 |
v0.9.1 |
A 97/100 | 0 | 1.10.0 | 2026-07-25 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @shuji-bonji/pdf-reader-mcp --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 9 side by side →
MCP server providing tools to read PDF files.
MCP server for efficient PDF text extraction, search, and metadata retrieval for Claude Code
MCP server for reading and analyzing PDF files from local paths or URLs - enables AI assistants to work with PDFs
A Model Context Protocol (MCP) server that enables AI assistants (Claude, GitHub Copilot) to read, extract text, search, and analyze PDF files with full metadata and image extraction support
An MCP server providing tools to read PDF files.
A powerful MCP server for comprehensive PDF processing with OCR and diagram detection
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.