Mineru Document Explorer MCP Server
mineru-document-explorer
npm
v1.0.9
Published by opendatalab — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MinerU Document Explorer — Agent-native knowledge engine: hybrid search and deep reading over markdown, PDF, DOCX, PPTX with BM25, vector search, and LLM reranking
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 7 = 87. 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 |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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.
Findings 4
high Shell/command execution in server code (dist/backends/python-utils.js)MTC-SRC-002
In the server's implementation (`dist/backends/python-utils.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from "child_process"; import { join } from "path"; import { fileURLToPath } from "url"; import { parse
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/backends/python-utils.js
high Shell/command execution in server code (dist/cli/qmd.js)MTC-SRC-002
In the server's implementation (`dist/cli/qmd.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: wn as nodeSpawn } from "child_process"; import { fileURLToPath } from "url"; import { dirname, join as pathJoin, relativ
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/cli/qmd.js
high Shell/command execution in server code (dist/db.js)MTC-SRC-002
In the server's implementation (`dist/db.js:13`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execSync } from "child_process"; export const isBun = typeof globalThis.Bun !== "undefined"; let _Database; let _
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/db.js
medium Untrusted input concatenated into a command sink (dist/cli/qmd.js)MTC-SRC-009
In the server's implementation (`dist/cli/qmd.js:2239`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { commit = execSync(`git -C ${scriptDir} rev-parse --short HEAD`, { encoding: "utf-8", stdio: ["pipe", "pip
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/cli/qmd.js
Tools 15
Each tool and what it can reach — statically extracted from the published source.
doc_elementsno sensitive capabilitydoc_grepno sensitive capabilitydoc_linksno sensitive capabilitydoc_queryno sensitive capabilitydoc_readno sensitive capabilitydoc_tocno sensitive capabilitydoc_writeno sensitive capabilitygetno sensitive capabilitymulti_getno sensitive capabilityqueryno sensitive capability
Show 5 more tools ↓
statusno sensitive capabilitywiki_indexno sensitive capabilitywiki_ingestno sensitive capabilitywiki_lintno sensitive capabilitywiki_logno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan 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 |
|---|---|---|---|---|
v1.0.9 latest |
B 87/100 | 4 | 1.13.0 | 2026-09-07 |
Embed this score
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.
Verify this score yourself
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 mineru-document-explorer --onlineMore in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology