imagen-4-mcp
This server provides focused access to Google's Imagen 4 image generation models via RunAPI, enabling AI agents to create, monitor, and price image generation tasks.
text_to_image: Generate images from text usingimagen-4,imagen-4-fast, orimagen-4-ultra. Supports aspect ratio (1:1, 16:9, 9:16, 3:4, 4:3), output count (1–4 images), and optional polling until completion.remix_image: Transform existing images using theimagen-4-pro-remix-imagemodel, with controls for aspect ratio, output format (PNG/JPG), output resolution (1k/2k/4k), and optional polling until completion.get_task: Fetch the current status and result payload (including output URLs) for any previously created task by providing its task ID and action type.check_pricing: Look up current pricing for any Imagen 4 model and endpoint — no API key required, useful for cost estimation before task creation.
Tasks can optionally wait for completion or be submitted and polled later. Configuration is via the RUNAPI_API_KEY environment variable or ~/.config/runapi/config.json, and the server is compatible with any MCP-compatible host (Claude Code, Cursor, Windsurf, VS Code, etc.).
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., "@imagen-4-mcp Generate a photo of a sunset over mountains."
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.
Why This Package?
@runapi.ai/imagen-4-mcp is a focused Model Context Protocol server for the Imagen 4 model line on RunAPI.
It gives MCP-compatible assistants direct access to 2 endpoints and 4 model variants without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to Imagen 4. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
Related MCP server: @runapi.ai/gemini-omni-mcp
Install
Add it to Claude Code:
claude mcp add imagen-4 -s user -- npx -y @runapi.ai/imagen-4-mcpUse project scope when the server should be shared with a repository:
claude mcp add imagen-4 -s project -- npx -y @runapi.ai/imagen-4-mcpCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"imagen-4": {
"command": "npx",
"args": ["-y", "@runapi.ai/imagen-4-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.
Tools
Tool | Auth | Purpose |
| Yes | Create an Imagen 4 remix image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create an Imagen 4 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 Imagen 4 model and endpoint. |
Models
Imagen 4 covers 4 model variants across 2 endpoints. Each tool accepts the models listed for it:
Tool | Models |
|
|
|
|
Model availability can change between releases. Use check_pricing or the Imagen 4 model page for the current catalog view.
Agent Prompts
Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
Create a task
Run an Imagen 4 remix image task with RunAPI.The assistant can call check_pricing, then remix_image, and return the task id, status, and output URLs.
Submit without waiting
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 pricing before creating
Check current Imagen 4 pricing, then create the task if it matches my request.The assistant calls check_pricing and can link to the Imagen 4 model page for the canonical catalog entry.
Configuration
The server resolves auth in this order:
RUNAPI_API_KEYenvironment variable, useful for headless and CI hosts~/.config/runapi/config.json, created by the MCPlogintool orrunapi loginNo 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.
Links
Resource | URL |
Imagen 4 model page | |
npm package | |
GitHub repository | |
RunAPI MCP overview | |
RunAPI docs |
License
Licensed under the Apache License, Version 2.0.
Available Tools
5 toolscheck_pricingC
Look up RunAPI pricing for the imagen-4 model line.
Inputs: model, action.
get_taskB
Fetch the current status and latest result payload for a imagen-4 task.
Inputs: action (required), task_id (required).
loginA
Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
Inputs: force.
remix_imageC
Create a Imagen 4 task on RunAPI (remix image). Returns a task id, status, and output URLs.
Inputs: source_image_urls (required), wait, model, prompt, +6 more.
text_to_imageC
Create a Imagen 4 task on RunAPI (text to image). Returns a task id, status, and output URLs.
Inputs: seed, wait, model, prompt, +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct action: auth, pricing lookup, two generation modes, and task retrieval. remix_image and text_to_image both create Imagen 4 tasks but their descriptions clearly differentiate modality, so confusion is minimal.
All tools use a consistent snake_case verb_noun or single-verb pattern (login, check_pricing, remix_image, text_to_image, get_task). No mixed conventions or casing deviations.
Five tools is well-scoped for an image-generation API wrapper: auth, pricing, two generation entry points, and a status poller. Each earns its place without redundancy.
Core lifecycle is covered: submit generation (text/remix), poll with get_task, check pricing, and authenticate. Minor gaps exist around task management (e.g. list tasks, cancel task), but the primary workflow has no dead ends.
Maintenance
Related MCP Connectors
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
MCP server for Pixapi: check live credit pricing and balance, then generate images and video.
MCP server for Qwen Image 3 AI image generation
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
AlicenseBqualityBmaintenanceRunAPI MCP server for the Flux 2 model line. Create tasks, poll their status, and check pricing through a single RunAPI API key.569 npmApache 2.0- AlicenseBqualityBmaintenanceMCP server for the Gemini Omni model line, enabling task creation (audio, character, text-to-video) and pricing checks through RunAPI.6217 npmApache 2.0
- AlicenseBqualityBmaintenanceMCP server for GPT-4o Image model line, enabling text-to-image task creation, status polling, and pricing checks via RunAPI.4204 npmApache 2.0
- AlicenseAqualityBmaintenanceRunAPI MCP server for the Hailuo model line. Create tasks, poll their status, and check pricing through a single RunAPI API key.578 npmApache 2.0