This server provides AI agents with an MCP interface to RunAPI's Midjourney services, supporting:
Image generation: Create images from text with text_to_image.
Image editing: Edit images using edit_image, optionally with masking.
Video generation: Convert images to video (image_to_video) and extend existing videos (extend_video).
Prompt tools: Get seed (get_seed), generate prompts from images (image_to_prompt), and shorten prompts (shorten_prompt) — all synchronous.
Task management: Create async tasks with optional waiting; poll status/results via get_task.
Pricing: Check current pricing for models/endpoints with check_pricing, no auth required.
Authentication: Log in via browser PKCE flow or provide an API key in environment/config.
Integration: Works with Claude Code, Cursor, VS Code, and any MCP-compatible host.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@RunAPI Midjourney MCP Server Generate a Midjourney image of a futuristic city at night."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@runapi.ai/midjourney-mcp is a focused Model Context Protocol server for the Midjourney model line on RunAPI.
It gives MCP-compatible assistants direct access to 7 endpoints and 3 model variants without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to Midjourney. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
Related MCP server: MidjourneyMCP
Add it to Claude Code:
claude mcp add midjourney -s user -- npx -y @runapi.ai/midjourney-mcpUse project scope when the server should be shared with a repository:
claude mcp add midjourney -s project -- npx -y @runapi.ai/midjourney-mcpCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"midjourney": {
"command": "npx",
"args": ["-y", "@runapi.ai/midjourney-mcp"]
}
}
}check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login.
Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.
Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.
Tool | Auth | Purpose |
| Yes | Create a Midjourney edit image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Midjourney extend video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Run a Midjourney get seed operation synchronously. Returns the operation result. |
| Yes | Run a Midjourney image to prompt operation synchronously. Returns the operation result. |
| Yes | Create a Midjourney image to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Run a Midjourney shorten prompt operation synchronously. Returns the operation result. |
| Yes | Create a Midjourney text to image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Fetch the current status and latest payload for an existing task. |
| No | Look up current pricing for a Midjourney model and endpoint. |
Midjourney covers 3 model variants across 7 endpoints. Each tool accepts the models listed for it:
Tool | Models |
|
|
|
|
| no model parameter |
| no model parameter |
|
|
| no model parameter |
|
|
Model availability can change between releases. Use check_pricing or the Midjourney model page for the current catalog view.
Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
Run a Midjourney edit image task with RunAPI.The assistant can call check_pricing, then edit_image, and return the task id, status, and output URLs.
Create the task but don't wait for it to finish.The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.
Check current Midjourney pricing, then create the task if it matches my request.The assistant calls check_pricing and can link to the Midjourney model page for the canonical catalog entry.
The server resolves auth in this order:
RUNAPI_API_KEY environment variable, useful for headless and CI hosts
~/.config/runapi/config.json, created by the MCP login tool or runapi login
No key, which still allows check_pricing
The config file is normally managed by login. A pre-provisioned headless config can use:
{
"apiKey": "your_runapi_key"
}Do not commit real API keys.
Resource | URL |
Midjourney model page | |
npm package | |
GitHub repository | |
RunAPI MCP overview | |
RunAPI docs |
Licensed under the Apache License, Version 2.0.
Look up RunAPI pricing for the midjourney model line.
Inputs: model, action.
Create a Midjourney task on RunAPI (edit image). Returns a task id, status, and output URLs.
Inputs: prompt (required), source_image_url (required), wait, model, +5 more.
Create a Midjourney task on RunAPI (extend video). Returns a task id, status, and output URLs.
Inputs: source_task_id (required), wait, model, prompt, +3 more.
Run a synchronous Midjourney operation on RunAPI (get seed). Returns the operation result.
Inputs: image_id (required).
Fetch the current status and latest result payload for a midjourney task.
Inputs: action (required), task_id (required).
Run a synchronous Midjourney operation on RunAPI (image to prompt). Returns the operation result.
Inputs: source_image_url (required).
Create a Midjourney task on RunAPI (image to video). Returns a task id, status, and output URLs.
Inputs: source_image_url (required), wait, model, prompt, +6 more.
Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
Inputs: force.
Run a synchronous Midjourney operation on RunAPI (shorten prompt). Returns the operation result.
Inputs: prompt (required).
Create a Midjourney task on RunAPI (text to image). Returns a task id, status, and output URLs.
Inputs: prompt (required), wait, model, timeout_ms, +4 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Each tool targets a distinct Midjourney action or resource: text_to_image, edit_image, extend_video, image_to_video, image_to_prompt, shorten_prompt, get_seed, get_task, check_pricing, and login. The split between synchronous operations (get_seed, image_to_prompt, shorten_prompt) and task-creating operations is clearly signaled in descriptions. No two tools appear to do the same thing.
Names are consistently snake_case and mostly follow a verb_noun or noun_to_noun pattern. Minor deviations exist: 'login' is a bare verb without an object, and 'text_to_image'/'image_to_video' lack an explicit action verb, but the set remains highly readable and predictable.
10 tools are well-scoped for a Midjourney API wrapper, covering core image/video operations, task status, pricing, and authentication without excessive overlap or bloat.
Core operations like text_to_image, edit_image, and various video tools are present, plus task status and pricing. However, notable Midjourney features such as upscale, variation, blend, or task cancellation/listing are absent, leaving some common workflows without a direct tool.
Create images & video from any MCP agent — 17 models, spend limits, one URL.
MCP server for Midjourney AI image generation and editing
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for Pixapi: check live credit pricing and balance, then generate images and video.
