Smart Reader MCP Server
@sylphx/smart-reader-mcp
npm
v0.2.11
Published by @sylphx — 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.
One MCP call reads PDF, image, or video by sniffing format and delegating to Sylphx Reader siblings.
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 − 7 = 93. 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 7
high Dynamic code execution in server code (dist/doctor-cli.js)MTC-SRC-001
In the server's implementation (`dist/doctor-cli.js:2894`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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 makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const val
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/doctor-cli.js
high Shell/command execution in server code (dist/doctor-cli.js)MTC-SRC-002
In the server's implementation (`dist/doctor-cli.js:7042`): 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: { var cp = __require("child_process"); var parse5 = require_parse(); var enoent = require_enoent(); function spa
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/doctor-cli.js
high Shell/command execution in server code (src/compose/composeVideoObjects.ts)MTC-SRC-002
In the server's implementation (`src/compose/composeVideoObjects.ts:155`): 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: } = await import('node:child_process'); const { existsSync } = await import('node:fs'); if (!existsSync('/u
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 src/compose/composeVideoObjects.ts
high Shell/command execution in server code (src/doctor.ts)MTC-SRC-002
In the server's implementation (`src/doctor.ts:1`): 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: spawnSync } from 'node:child_process'; import { existsSync } from 'node:fs'; import { createRequire } from 'node:module
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 src/doctor.ts
high Shell/command execution in server code (src/engine/rust-sniff.ts)MTC-SRC-002
In the server's implementation (`src/engine/rust-sniff.ts:1`): 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: spawnSync } from 'node:child_process'; import { existsSync } from 'node:fs'; import path from 'node:path'; import { fil
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 src/engine/rust-sniff.ts
medium Dynamic module load from a non-literal (src/compose/composeVideoObjects.ts)MTC-SRC-005
In the server's implementation (`src/compose/composeVideoObjects.ts:131`): 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 mod = await import(specifier).catch(() => { throw new Error(hint); }); return instantiateSdk(m
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 src/compose/composeVideoObjects.ts
medium Dynamic module load from a non-literal (src/delegate/delegateToReader.ts)MTC-SRC-005
In the server's implementation (`src/delegate/delegateToReader.ts:83`): 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 packageJson = require(packageJsonPath) as { bin?: string | Record<string, string>; }; const binF
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 src/delegate/delegateToReader.ts
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 4
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 |
|---|---|---|---|---|
v0.2.11 latest |
A 93/100 | 7 | 1.13.0 | 2026-09-07 |
v0.2.5 |
A 93/100 | 5 | 1.12.1 | 2026-08-02 |
v0.2.3 |
A 93/100 | 5 | 1.12.1 | 2026-08-01 |
v0.2.1 |
A 93/100 | 3 | 1.12.1 | 2026-07-31 |
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 @sylphx/smart-reader-mcp --onlineMore in Data Science & ML
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
Add MCP servers to your favorite coding agents with a single command.
Help agents automatically write and test stories for your UI components
Model Context Protocol server for AI-Archive platform - enables AI agents to discover, submit, and review research papers
MCP server for Semantic Scholar research workflows with stdio and Streamable HTTP transports.