Install MCP Plugin

Prerequisites

Node.js 18+ installed
At least one generation provider (for generate_image / generate_video):
- MeiGen Cloud — an API key from meigen.ai (Settings → API Keys)
- ComfyUI — a running ComfyUI server (installation guide)
- OpenAI-Compatible API — your own key from any provider (Together AI, Fireworks AI, OpenAI, etc.)

You don’t need a provider to get started. Gallery search, prompt enhancement, and inspiration tools work without any API key.

Installation

Prefer zero installation? The remote MCP endpoint needs no Node.js, no npx, and no local config file — just point any MCP host at https://www.meigen.ai/api/mcp over HTTP.

Claude Code Plugin (Recommended)

Install the plugin

# Add the plugin marketplace
/plugin marketplace add jau123/MeiGen-AI-Design-MCP

# Install
/plugin install meigen@meigen-marketplace

Restart Claude Code after installation (close and reopen, or open a new terminal tab).

Configure a provider

Start a new Claude Code session and run /meigen:setup. The setup wizard will guide you through provider selection and API key configuration on macOS, Linux, and Windows.Alternatively, set environment variables directly (see Provider Configuration below).

Start using it

Ask Claude to generate images or videos naturally:

“Generate a minimalist logo for a coffee shop”
“Animate this photo into a 5-second clip”
“Search the gallery for cyberpunk cityscapes”
“Enhance this prompt: a cat in space”

Also listed on the community wshobson/agents marketplace. That listing doesn’t bundle MCP server config — after installing, add the JSON block from Other MCP-Compatible Hosts to .mcp.json yourself.

Cursor / VS Code / Windsurf / Roo Code

One command writes the right MCP config file for each editor:

npx meigen init cursor      # writes .cursor/mcp.json
npx meigen init vscode      # writes .vscode/mcp.json
npx meigen init windsurf    # writes ~/.codeium/windsurf/mcp_config.json
npx meigen init roo         # writes .roo/mcp.json
npx meigen init claude      # writes .mcp.json (Claude Code project-level)

After the config is written, set MEIGEN_API_TOKEN in your shell and restart the host. On hosts that don’t support the /meigen:setup slash command, add the token to the env block of the meigen server entry directly.

OpenAI Codex CLI

Codex uses TOML. Add to ~/.codex/config.toml:

[mcp_servers.meigen]
command = "npx"
args = ["-y", "meigen@latest"]

[mcp_servers.meigen.env]
MEIGEN_API_TOKEN = "meigen_sk_..."

Hermes Agent (NousResearch)

Hermes is a first-class MCP client. Add to ~/.hermes/config.yaml:

mcp_servers:
  meigen:
    command: "npx"
    args: ["-y", "meigen@latest"]
    env:
      MEIGEN_API_TOKEN: "meigen_sk_..."
    timeout: 2700          # long videos (e.g. reference-video continuation) can exceed 15 min
    connect_timeout: 120   # first npx download can be slow

Set timeout to 2700, not the Hermes default (120s). Long video generations — especially reference-video continuation — can run past 15 minutes. A shorter timeout disconnects Hermes while the job is still running server-side, after credits have already been deducted. connect_timeout: 120 covers the first slow npx download.If a session does disconnect mid-generation, don’t resubmit — call check_generation with the generationId from your original request to resume tracking it. Resubmitting starts a new generation and deducts credits again.

Standalone CLI (no MCP host required)

For shell scripts, CI pipelines, or anyone who wants AI image generation without an MCP host:

# Auth once
export MEIGEN_API_TOKEN=meigen_sk_...

# Generate
npx meigen gen --prompt "a calico cat in a sunlit kitchen"

# With a specific model + aspect ratio
npx meigen gen -p "logo design" -m midjourney-v8.1 -r 1:1

# With a reference image (local path auto-uploaded)
npx meigen gen -p "product hero shot" --ref ~/Desktop/bottle.jpg

# Submit only — print generationId without polling (good for CI)
npx meigen gen -p "..." --no-wait

# Machine-readable output (good for jq pipes)
npx meigen gen -p "..." --json | jq -r '.imageUrls[0]'

Generated images save to ~/Pictures/meigen/ by default — see Output Directories to change where files land.

OpenClaw

Install the full plugin from ClawHub (includes commands, skills, and MCP server):

openclaw bundles install clawhub:meigen-ai-design

Or install only the skill (no commands/agents):

npx clawhub@latest install creative-toolkit

OpenClaw uses the Agent Skills open standard. No MCP configuration needed — the skill handles everything.

Other MCP-Compatible Hosts

For any host that consumes stdio MCP, add this to its config file:

{
  "mcpServers": {
    "meigen": {
      "command": "npx",
      "args": ["-y", "meigen@latest"],
      "env": {
        "MEIGEN_API_TOKEN": "meigen_sk_..."
      }
    }
  }
}

Provider Configuration

Configure one or more providers. When multiple are available, the plugin selects in order: MeiGen → ComfyUI → OpenAI-compatible. You can override this per-request.

MeiGen Cloud

The easiest way to get started. MeiGen’s hosted API gives you image and video models from OpenAI, Google, ByteDance, Midjourney, xAI, Black Forest Labs, Alibaba, and Agnes — no GPU required. Call list_models for the current lineup, or see the model comparison for capabilities and pricing.

Variable	Value
`MEIGEN_API_TOKEN`	Your API key starting with `meigen_sk_`

Get your API key: sign in at meigen.ai → click your avatar → Settings → API Keys → create a new key.

API keys can only use purchased credits, not daily free credits. Ensure your account has purchased credits before generating via the plugin.

Bring Your Own API (OpenAI-Compatible)

Connect any image generation API that follows the OpenAI format — Together AI, Fireworks AI, DeepInfra, SiliconFlow, OpenAI, or your own endpoint.

Variable	Value
`OPENAI_API_KEY`	Your API key from the provider
`OPENAI_BASE_URL`	API endpoint (e.g., `https://api.together.xyz/v1`)
`OPENAI_MODEL`	(Optional) Model name at your provider

Set OPENAI_BASE_URL to point to your provider’s endpoint. If omitted, defaults to OpenAI’s API.

ComfyUI (Local)

Run image generation on your own GPU with full control over models, samplers, and workflows. Free to use — no API key needed.

Variable	Value
`COMFYUI_URL`	ComfyUI server address (default: `http://127.0.0.1:8188`)

Requirements:

ComfyUI must be running and accessible at the configured URL
You need at least one imported workflow template — see the ComfyUI Guide

ComfyUI runs serially: one image at a time.

Output Directories

Generated files are written to disk by both the MCP tools and the standalone CLI.

Type	Default location	Override	Linux fallback
Images	`~/Pictures/meigen/`	`MEIGEN_OUTPUT_DIR`	`XDG_PICTURES_DIR`
Videos	`~/Movies/meigen/`	`MEIGEN_VIDEO_OUTPUT_DIR`	`XDG_VIDEOS_DIR`

Set these the same way as your provider variables — in the env block of your MCP config, or exported in your shell for CLI use.

Verify Installation

After setup, ask your AI assistant:

“List the available models”

If configured correctly, it will call the list_models tool and show models from all your configured providers.

Usage

Once installed, ask your AI assistant in plain language — for example, “Generate a watercolor landscape, 16:9 aspect ratio”. See the overview for the full list of tools.

Troubleshooting

'No image generation providers configured'

No provider is set up. On Claude Code, run /meigen:setup (interactive wizard). On other hosts (Cursor, Codex, Windsurf, Hermes Agent, etc.), add the env var to your MCP config file directly:

MeiGen: MEIGEN_API_TOKEN
OpenAI-compatible: OPENAI_API_KEY
ComfyUI: COMFYUI_URL (and import a workflow)

Then restart the host.

'Insufficient credits' (MeiGen)

API keys can only use purchased credits, not daily free credits. Purchase credits at meigen.ai.

ComfyUI connection refused

Make sure ComfyUI is running (python main.py in the ComfyUI directory)
Check that COMFYUI_URL matches the address shown when ComfyUI starts (default: http://127.0.0.1:8188)
If running on a different machine, ensure the port is accessible

ComfyUI generation fails

Open the ComfyUI web UI and check for error messages
Use comfyui_workflow view to inspect the workflow nodes
Ensure the checkpoint model referenced in the workflow is actually downloaded
Try running the workflow manually in ComfyUI first

Plugin not showing in tool list

Make sure Node.js 18+ is installed
Try running npx -y meigen directly to check for errors
Restart your editor
Check that the MCP configuration JSON is valid

Generation timeout

Generation times vary by model — MeiGen Cloud image models typically finish in well under a minute; video generation takes longer, especially with reference-video continuation. Polling isn’t capped by a fixed 5- or 8-minute client timeout — it follows the server’s own progress signal, with only a 45-minute safety valve against a fully hung connection.If your session disconnects or polling gets interrupted, don’t resubmit the same request — call check_generation with the generationId from your original request to resume tracking it. Resubmitting starts a new generation and deducts credits again.ComfyUI generation is still capped at 5 minutes (depends on your local GPU).

Changes to config not taking effect

After modifying ~/.config/meigen/config.json or environment variables, you must restart your editor (or start a new Claude Code session) for changes to take effect.

Getting Started

Features

MCP Plugin

Account

Prerequisites

Installation

Claude Code Plugin (Recommended)

Cursor / VS Code / Windsurf / Roo Code

OpenAI Codex CLI

Hermes Agent (NousResearch)

Standalone CLI (no MCP host required)

OpenClaw

Other MCP-Compatible Hosts

Provider Configuration

MeiGen Cloud

Bring Your Own API (OpenAI-Compatible)

ComfyUI (Local)

Output Directories

Verify Installation

Usage

Troubleshooting

​Prerequisites

​Installation

​Claude Code Plugin (Recommended)

​Cursor / VS Code / Windsurf / Roo Code

​OpenAI Codex CLI

​Hermes Agent (NousResearch)

​Standalone CLI (no MCP host required)

​OpenClaw

​Other MCP-Compatible Hosts

​Provider Configuration

​MeiGen Cloud

​Bring Your Own API (OpenAI-Compatible)

​ComfyUI (Local)

​Output Directories

​Verify Installation

​Usage

​Troubleshooting

Prerequisites

Installation

Claude Code Plugin (Recommended)

Cursor / VS Code / Windsurf / Roo Code

OpenAI Codex CLI

Hermes Agent (NousResearch)

Standalone CLI (no MCP host required)

OpenClaw

Other MCP-Compatible Hosts

Provider Configuration

MeiGen Cloud

Bring Your Own API (OpenAI-Compatible)

ComfyUI (Local)

Output Directories

Verify Installation

Usage

Troubleshooting