Image Gen runs on your own machine — the client starts it, so there is no endpoint to ping. 79 installs a week from npm. Last commit 13 Aug 2026.
Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.
We read the source, 1 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const chosen = uniquePath(path.join(dir, name), taken);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add image-gen -- npx -y @nuver-labs/image-gen-mcp
{
"mcpServers": {
"image-gen": {
"args": [
"-y",
"@nuver-labs/image-gen-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.image-gen]
command = "npx"
args = ["-y", "@nuver-labs/image-gen-mcp"]
{
"mcpServers": {
"image-gen": {
"args": [
"-y",
"@nuver-labs/image-gen-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"image-gen": {
"args": [
"-y",
"@nuver-labs/image-gen-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GEMINI_API_KEY (Google Gemini API key. Enables the Gemini provider. At least one provider key is required.), OPENAI_API_KEY (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.).
The author declared them in the registry entry; get the values from the project itself.
Generate images, videos, speech, music and text with HiAPI's AI models. Bring your own API key.
Generate images and video from text prompts across Gemini, OpenAI and Kie AI.
Generate and edit images and video via OpenRouter or any OpenAI-compatible API.
Generate, edit and upscale AI video and images from any agent via VicSee.
Generate and edit images with Google Gemini (Nano Banana / Nano Banana Pro) image models.
Generate and edit images and videos with imageat.
Generate images with your own ChatGPT subscription (Plus, Pro or Team), without spending API credits
Generate on-brand images from your AI agent: design, edit, and render templates over MCP.
Answers built from our own checks of this server.