cascade-img runs on your own machine — the client starts it, so there is no endpoint to ping. 87 installs a week from pypi. Last commit 18 Jul 2026.
LLM-operable Midjourney pipeline: 21 MCP tools to compose, generate, curate with vision, and log.
What the code does
We read the source, 2 d ago · rules 995398eba69f
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.
return subprocess.Popen(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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.
claude mcp add cascade-img -e 'DISCORD_USER_TOKEN=<DISCORD_USER_TOKEN>' -e 'MJ_CHANNEL_ID=<MJ_CHANNEL_ID>' -e 'MJ_IMAGINE_VERSION=<MJ_IMAGINE_VERSION>' -- uvx cascade-img{
"mcpServers": {
"cascade-img": {
"command": "uvx",
"args": [
"cascade-img"
],
"env": {
"DISCORD_USER_TOKEN": "<DISCORD_USER_TOKEN>",
"MJ_CHANNEL_ID": "<MJ_CHANNEL_ID>",
"MJ_IMAGINE_VERSION": "<MJ_IMAGINE_VERSION>"
}
}
}
}[mcp_servers.cascade-img]
command = "uvx"
args = ["cascade-img"]
env = { DISCORD_USER_TOKEN = "<DISCORD_USER_TOKEN>", MJ_CHANNEL_ID = "<MJ_CHANNEL_ID>", MJ_IMAGINE_VERSION = "<MJ_IMAGINE_VERSION>" }{
"mcpServers": {
"cascade-img": {
"command": "uvx",
"args": [
"cascade-img"
],
"env": {
"DISCORD_USER_TOKEN": "<DISCORD_USER_TOKEN>",
"MJ_CHANNEL_ID": "<MJ_CHANNEL_ID>",
"MJ_IMAGINE_VERSION": "<MJ_IMAGINE_VERSION>"
}
}
}
}{
"servers": {
"cascade-img": {
"type": "stdio",
"command": "uvx",
"args": [
"cascade-img"
],
"env": {
"DISCORD_USER_TOKEN": "<DISCORD_USER_TOKEN>",
"MJ_CHANNEL_ID": "<MJ_CHANNEL_ID>",
"MJ_IMAGINE_VERSION": "<MJ_IMAGINE_VERSION>"
}
}
}
}Put your own values in place of
<DISCORD_USER_TOKEN> (Discord user-account token the bridge daemon uses to talk to Midjourney (captured from the Discord desktop app; see RUNBOOK.md)), <MJ_CHANNEL_ID> (Discord channel ID where the Midjourney bot runs), <MJ_IMAGINE_VERSION> (Version token for Midjourney's /imagine slash command, captured from Discord).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
CASCADE_BRIDGE_URL (URL of the running cascade-mj-bridge daemon that cascade-mcp forwards to).
Alternatives to cascade-img
same job, measured the same wayRun 3D CAD operations, pipelines, parametric models and STEP conversions on CAD Cloud with a key
Host, Docker, Compose, SSH, logs and ZFS operations via two action-router tools.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
React dashboard components — API lookup, code generation, and prop validation for AI tools.
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
Managed MCP gateway with OAuth, per-agent permissions, shared accounts and activity logs.
Managed MCP gateway with OAuth, per-agent permissions, shared accounts and activity logs.
DataOps ClickHouse MCP server with query optimization and pipeline monitoring
cascade-img — questions
Answers built from our own checks of this server.