AgentArmorHQ
Sign in

mcp-image

Skill · npm · ★ 185 · graded 2026-10-24Source linked

MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.

No outside reports on file

Use this safely by storing API keys in environment variables only, never trusting untrusted input for image prompts, and understanding that all your image requests go to external companies.

Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for MCP Image helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachLocal or standard API callsLOW
  • CredentialsRequires API key or tokenREVIEW
  • Package sourcenpm (mcp-image)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

npx -y mcp-image

All setup options ↓

Check this skillWatch it in my stackCompareAdd to allowlistREADME badgeView project

About MCP Image

This is a server tool that lets AI agents generate and edit images using three different services: Nano Banana (Gemini), OpenAI, and BytePlus Seedream. It automatically improves image prompts and offers quality settings to control the output.

Who it’s for

Developers building AI applications that need image generation features. It's useful if you want to switch between multiple image providers without rewriting code.

Alternatives

  • OpenAI API direct (image generation only from one provider, simpler setup)
  • Replicate (supports many open-source image models, pay-per-use)
  • Hugging Face Inference API (open-source models, can run locally)
  • Stability AI (Stable Diffusion hosted service with good documentation)

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README for installation and configuration details, as setup depends on which image services you want to use and their API keys.

Why this grade

BB — Some risk signals

Signal-based grade (4/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

55/100
GitHub stars
185
Weekly npm downloads
1.8k
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-30).

Check a specific version →

Risks to watch for

  • API credentials exposed: Requires API keys from three different image services; if stored insecurely, attackers could use your accounts and bill charges to you
  • Prompt injection attacks: Malicious text fed to the AI could craft harmful image requests that bypass safety filters or generate unwanted content
  • Data sent to external services: All image prompts and generation requests travel to third-party companies (OpenAI, Gemini, BytePlus); those companies log and process this data
  • Unvetted prompt optimization: The automatic prompt improvement feature could change your requests in unexpected ways or amplify biases
  • Supply chain risk: The tool itself is maintained by an individual developer; updates or security patches depend on their continued involvement

How to lower the risk

Least-privilege permissions

  • Give API keys only read/write access to image generation, never account management
  • Rotate API keys every 90 days and immediately if compromised

Network isolation

  • Block direct outbound connections except to the three image services you use
  • Monitor which prompts actually reach the external APIs

Monitoring

  • Log all image generation requests and their results
  • Set up billing alerts on all three image services to catch unexpected usage

Red flags to watch for

  • Unusual image requests or spike in usage volume
  • API keys appearing in logs or error messages
  • Changes to the prompt optimization behavior after updates

Questions

How do I install MCP Image?

Install MCP Image with npm install mcp-image or run it directly with npx -y mcp-image. For agent integration and configuration flags, see the documentation at github.com/shinpr/mcp-image. Pin an exact version and pass --ignore-scripts if you want to block post-install hooks.

Are there security reports about MCP Image?

No reports found for this package in our research (last checked 2026-10-30). MCP Image currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include api credentials exposed, prompt injection attacks, data sent to external services.

Is MCP Image actively maintained?

MCP Image has 185 GitHub stars and 1.8k weekly npm downloads. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/shinpr/mcp-image before pinning it in production.

What are alternatives to MCP Image?

Notable alternatives to MCP Image include OpenAI API direct, Replicate, Hugging Face Inference API, Stability AI. You can also compare MCP Image side by side with other skills in the Related tools section on this page.

README badge and team notes

Maintain or use MCP Image? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade B for MCP Image

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for MCP Image](https://agentarmorhq.com/api/badge/shinpr-mcp-image)](https://agentarmorhq.com/skills/shinpr-mcp-image)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/shinpr-mcp-image"><img src="https://agentarmorhq.com/api/badge/shinpr-mcp-image" alt="AgentArmorHQ Risk Grade for MCP Image" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "shinpr-mcp-image"

Share with your security lead

Need sign-off to use mcp-image? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: mcp-image
- **Listing URL:** https://agentarmorhq.com/skills/shinpr-mcp-image
- **Type:** AI agent skill
- **Risk Grade:** Grade B (Some risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 185 GitHub stars, 1.8k weekly npm downloads

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Local or standard API calls
- **Credentials:** Requires API key or token
- **Package source:** npm (mcp-image)

#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts mcp-image`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
AI agent skill
Publisher
shinpr
Source code
github.com/shinpr/mcp-image
Install command
npm install mcp-image
Est. context load
~70 tokens idle · ~450 tokens when active (on-demand skill)
Popularity
185 GitHub stars, 1.8k weekly npm downloads
Last updated
2026-10-29
Last graded
2026-10-24

Community

Discussions for MCP Image

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for MCP Image helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude