media-gen-mcp-server
npm
v0.19.0
Published by wangdong233 — 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.
All-in-one image-generation MCP server for Claude Code: AI imagery/video (Agnes AI + Zhipu) + structured local rendering (diagrams, charts, formulas, cards, icons, QR codes). Provider- and engine-pluggable.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Hardcoded Google API key in server code MTC-SRC-008 | exfiltration |
2. Client adoption risk — 99 − 7 = 92. 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.
In the server's implementation (`dist/providers/flow.js:391`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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: .value; } async eval(expr, timeoutMs) { try { return await this.evalOnce(expr, timeoutMs);
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/providers/flow.js
In the server's implementation (`dist/providers/flow.js:391`): 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: .value; } async eval(expr, timeoutMs) { try { return await this.evalOnce(expr, timeoutMs);
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/providers/flow.js
In the server's implementation (`dist/browser-pool.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: { execFile } from "node:child_process"; import { promisify } from "node:util"; import path from "node:path"; /** * brow
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/browser-pool.js
In the server's implementation (`dist/checks/output-checker.js:22`): 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 path from "node:path"; 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 dist/checks/output-checker.js
In the server's implementation (`dist/render-video.js: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 fs from "node:fs"; import path from "node:path"; import os from "node:os"
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/render-video.js
In the server's implementation (`dist/providers/flow.js:297`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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 res = await fetch(`http://${CDP_HOST}:${this.port}/json/list`, { signal: AbortSignal.timeout
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/providers/flow.js
A hardcoded Google API key (a client API key (restricted by referrer/quota, not a private secret)) appears in `dist/providers/flow.js:37`. Verify whether this is a real credential; if so, remove and rotate it.
Evidence: Google API key: AIza…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server dist/providers/flow.js
Each tool and what it can reach — statically extracted from the published source.
flow_statusingests untrusted inputgenerate_iconingests untrusted inputgenerate_imageingests untrusted inputget_videoingests untrusted inputanalyze_chartno sensitive capabilitycreate_videono sensitive capabilitydescribe_imageno sensitive capabilityextract_image_metano sensitive capabilityextract_pdfno sensitive capabilityextract_tableno sensitive capabilityextract_textno sensitive capabilitygenerate_cardno sensitive capabilitygenerate_chartno sensitive capabilitygenerate_diagramno sensitive capabilitygenerate_formulano sensitive capabilitygenerate_interactive_diagramno sensitive capabilitygenerate_nested_diagramno sensitive capabilitygenerate_qrcodeno sensitive capabilityget_pdfno sensitive capabilitylist_modelsno sensitive capabilitylist_vision_capabilitiesno sensitive capabilityrender_svgno sensitive capabilityrender_videono 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 |
|---|---|---|---|---|
v0.19.0 latest |
A 92/100 | 7 | 1.13.0 | 2026-09-07 |
v0.17.1 |
A 92/100 | 6 | 1.13.0 | 2026-09-01 |
v0.15.0 |
A 92/100 | 6 | 1.13.0 | 2026-08-31 |
v0.14.0 |
A 93/100 | 2 | 1.13.0 | 2026-08-27 |
v0.13.1 |
A 93/100 | 2 | 1.12.1 | 2026-08-12 |
v0.12.1 |
A 93/100 | 2 | 1.12.1 | 2026-07-28 |
v0.11.0 |
A 100/100 | 1 | 1.5.0 | 2026-07-22 |
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 media-gen-mcp-server --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 3 side by side →
MCP server for media generation
MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand