ima2-gen — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by lidge-ai · MCP Server · ★ 853

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ima2-gen safe to install? View the security audit →

About ima2-gen

Generate, branch and clean up images and video on your own machine. One local studio for GPT, Grok, Gemini, NovelAI and ComfyUI. Use it from the browser, the Mac app, the CLI, or hand it to your coding agent. <img src="https://img.shields

ai-agentgeminigrokimage-generationlocal-firstmcpnode-editoropenaivideo-generationvisual-workflow

Quick Facts

Stars853
Forks136
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score69.5073792852145/100
Open Issues2
Last Updated2026-10-03
Created2026-04-21
Platformsgemini, mcp, node
Est. Tokens~22k

Compatible Skills

These tools work well together with ima2-gen for enhanced workflows:

  • Flovart — semantic(0.37)+complementary+rare_topics+same_lang+similar_pop+shared_platform (72%)
  • ima2-gen — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (69%)
  • skills — semantic(0.37)+complementary+same_lang+similar_pop+shared_platform (63%)
  • nodetool — semantic(0.36)+complementary+same_lang+similar_pop+shared_platform (63%)
  • OpenLoaf — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)

ima2-gen alternative? Top 6 similar tools

Looking for a ima2-gen alternative? If you're comparing ima2-gen with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ima2-gen by lidge-jun · ⭐ 782

    Local-first visual generation runtime and studio for people and coding agents, with reproducible image and vid

  • comfyui-mcp by artokun · ⭐ 778

    Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video

  • py-gpt by szczyglis-dev · ⭐ 2.0k

    Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - c

  • UnrealGenAISupport by prajwalshettydev · ⭐ 650

    Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gem

  • nodetool by nodetool-ai · ⭐ 549

    Agent-first Creative Workspace

  • CoWork-OS by CoWork-OS · ⭐ 470

    Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ima2-gen?

ima2-gen is Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.. It is categorized as a MCP Server with 853 GitHub stars.

What programming language is ima2-gen written in?

ima2-gen is primarily written in TypeScript. It covers topics such as ai-agent, gemini, grok.

How do I install or use ima2-gen?

You can find installation instructions and usage details in the ima2-gen GitHub repository at github.com/lidge-ai/ima2-gen. The project has 853 stars and 136 forks, indicating an active community.

What license does ima2-gen use?

ima2-gen is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ima2-gen?

The top alternatives to ima2-gen on Agent Skills Hub include ima2-gen, comfyui-mcp, py-gpt. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools