InnerVault

Image Gen

Stale Official MCP Registry, com.nuverlabs

Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.

Open the source (opens github.com) https://github.com/nuver-labs/image-gen-mcp

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
  • Needs credentials: GEMINI_API_KEY, OPENAI_API_KEY. Use a key with the least access you can.

What it is

MCP servers from com.nuverlabs.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

npm package (stdio)

@nuver-labs/image-gen-mcp@0.2.1

From the server's entry in the official MCP Registry

Settings it asks for

  • GEMINI_API_KEY secret · Google Gemini API key. Enables the Gemini provider. At least one provider key is required.
  • OPENAI_API_KEY secret · OpenAI API key. Enables the OpenAI provider. At least one provider key is required.
  • IMAGE_GEN_MCP_DEFAULT_PROVIDER · Provider used when a tool call does not name one: gemini or openai. Defaults to whichever key is set, preferring gemini.
  • IMAGE_GEN_MCP_GEMINI_MODEL · Default Gemini model. Defaults to gemini-3.1-flash-image.
  • IMAGE_GEN_MCP_OPENAI_MODEL · Default OpenAI model. Defaults to gpt-image-2.
  • IMAGE_GEN_MCP_OUTPUT_DIR · Directory used when a tool call passes no output_path.
  • IMAGE_GEN_MCP_ALLOWED_DIRS · Comma separated directories that file reads and writes are confined to. Unset means unrestricted.
  • IMAGE_GEN_MCP_TIMEOUT_MS · Per-request timeout to the provider API in milliseconds. Defaults to 180000.
  • IMAGE_GEN_MCP_LOG_FILE · Path of the JSONL image ledger. Defaults to ~/.image-gen-mcp/images.jsonl. Set to none to disable the file.

Related

  1. claude-video-vision

    MCP servers

    Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

    Stale GitHub, jordanrendric 1,366 ★MITUpdated 33 days ago

    git clone https://github.com/jordanrendric/claude-video-vision.git
  2. openrouter-multimodal

    MCP servers

    Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.

    Stale Official MCP Registry, io.github.stabgan 101 ★Apache-2.0Updated 25 days ago 2 notes

    @stabgan/openrouter-mcp-multimodal@4.5.1
  3. fortemi

    MCP servers

    Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.

    Indexed GitHub, Fortemi 30 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/Fortemi/fortemi.git
  4. multimodal

    MCP servers

    Multi-provider media generation — images, video, audio, and transcription via a unified interface

    Stale Official MCP Registry, io.github.rsmdt Updated 8 months ago 2 notes

    @r16t/multimodal-mcp@1.3.1
  5. Ui.Vision MCP

    MCP servers

    MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input

    Stale Official MCP Registry, io.github.A9T9 2,075 ★Updated 2 months ago 1 note

    uivision-mcp-bridge@1.7.18
  6. Sia Studio

    MCP servers

    Sia Studio: generate images, reuse creative assets, and manage Productions in your workspace.

    Stale Official MCP Registry, vision.sia Updated 3 days ago 1 note