mcpbeat Sign in

Imagine MCP Server

local only

Imagine MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 1 316 installs a week from pypi. Last commit 13 Sep 2026.

MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

The author archived this repository on GitHub, meaning it is no longer maintained.

Installs per day peak 650 · avg 137 · +28% w/w
a month agotoday
1 316
Installs / week
pypi · imagine-mcp
4
Stars
1 open issues
13 Sep 2026
Last commit
0 releases in 90 days
Apache-2.0
License
Python

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add imagine-mcp -- uvx imagine-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "imagine-mcp": {
      "args": [
        "imagine-mcp"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.imagine-mcp]
command = "uvx"
args = ["imagine-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "imagine-mcp": {
      "args": [
        "imagine-mcp"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "imagine-mcp": {
      "args": [
        "imagine-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: UNDERSTAND_MODELS (Ordered model chain for the understand path 'provider/model,...' (order = litellm fallback; provider inferred from the prefix). Empty = understand off (provider/tier catalog default). Generation stays provider/tier native.), GEMINI_API_KEY (Google AI Studio API key (aistudio.google.com/apikey)), OPENAI_API_KEY (OpenAI API key (platform.openai.com)), XAI_API_KEY (xAI (Grok) API key (console.x.ai)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Imagine MCP

same job, measured the same way
MCP Grok
by acedatacloud

MCP server for Grok Imagine AI video generation

362 installs/wk answering
GPT Image
by codechap

MCP server for OpenAI GPT image generation and editing

local only
Media Gen MCP
by strato-space

MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.

33 installs/wk local only
Imgx
by somacoffeekyoto

AI image generation and editing MCP server. Gemini + OpenAI, iterative editing, undo/redo.

80 installs/wk local only
Grok Image
by codechap

MCP server for Grok image generation and editing

local only
MCP Imagenate
by mimo-3

MCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)

644 installs/wk local only
Google Image
by codechap

MCP server for Google Gemini image generation and editing

local only
MCP Kling
by acedatacloud

MCP server for Kling AI video generation

664 installs/wk answering

Imagine MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Imagine MCP?
Imagine MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package imagine-mcp was installed 1 316 times last week.
Is Imagine MCP still maintained?
The author archived this repository on GitHub, meaning it is no longer maintained. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect Imagine MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls imagine-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Imagine MCP?
The pypi package imagine-mcp was installed 1 316 times in the last week. Week over week that is +28%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Imagine MCP open source?
Yes — it is published under the Apache-2.0 licence, written in Python, 4 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.