npm TypeScript analyzed 4.1.3

SylphxAI/pdf-reader-mcp

v4.1.3
npm

Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.

maintainer
SylphxAI
licence
MIT
first seen
2026-05-22
last seen
2026-09-07
releases · 30d
0
short id
risk 32/100 · heuristic grade
B low inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • tool safety inferred + 5
  • supply-chain attested + 8
  • trust mitigators mixed − 16

attested inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 15 movements
  • C · 40 B · 32
  • C · 35 C · 40
  • C · 50 C · 35
  • C · 42 C · 50
  • B · 23 C · 42
  • B · 29 B · 23
  • C · 42 B · 29
  • B · 29 C · 42
  • C · 42 B · 29
  • A · 7 C · 42
  • B · 29 A · 7
  • C · 42 B · 29
  • B · 27 C · 42
  • B · 20 B · 27
  • B · 27 B · 20
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +5
  1. medium dangerous code

    dynamic exec: new Function()

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v4.1.3 · analyzer v33 · 4w ago

skills & prompt files 2

danger signals3

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:SylphxAI/pdf-reader-mcp/badge.svg)](https://mcpobservatory.com/servers/github:SylphxAI/pdf-reader-mcp/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of SylphxAI.