RunAPI Ideogram V3 MCP server gives MCP-compatible assistants scoped access to Ideogram V3 image generation, async task polling, and pricing.
Authenticate RunAPI with browser PKCE login (login), saving credentials to ~/.config/runapi/config.json; RUNAPI_API_KEY also works for headless/CI.
Create edit-image tasks (edit_image) with required source image and mask, plus optional prompt, model, style, seed, output count, rendering speed, reference images, callback, timeout, polling, and prompt expansion.
Create remix-image tasks (remix_image) from a source image with optional prompt, negative prompt, strength, style, aspect ratio, references, masks, style references, output count, rendering speed, callback, timeout, polling, and prompt expansion.
Create text-to-image tasks (text_to_image) with optional prompt, style, aspect ratio, negative prompt, references, output count, rendering speed, callback, timeout, polling, and prompt expansion.
The schema also exposes reframe-image tasks (reframe_image), but the README says this model was retired; new requests return HTTP 410, while existing tasks can still be queried.
Create tools optionally wait for terminal status and return task id, status, and output URLs.
Poll or fetch an existing task's status and latest result payload using get_task with task_id and action.
Check current pricing for a model/endpoint with check_pricing without authentication.
Work with 6 Ideogram V3 model variants across edit, remix, and text-to-image endpoints; availability can change, so use pricing or the model page.
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., "@Ideogram V3 MCP Server Generate an image of a serene beach at sunset."
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/ideogram-v3-mcp is a focused Model Context Protocol server for the Ideogram V3 model line on RunAPI.
It gives MCP-compatible assistants direct access to 3 endpoints and 6 model variants without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to Ideogram V3. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
ideogram-v3-reframe was retired on 2026-10-11T00:00:00Z. New requests return HTTP 410 before task creation or balance deduction. Existing tasks can still be queried. This model ID is not mapped to another model.
Related MCP server: @runapi.ai/gpt-4o-image-mcp
Add it to Claude Code:
claude mcp add ideogram-v3 -s user -- npx -y @runapi.ai/ideogram-v3-mcpUse project scope when the server should be shared with a repository:
claude mcp add ideogram-v3 -s project -- npx -y @runapi.ai/ideogram-v3-mcpCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"ideogram-v3": {
"command": "npx",
"args": ["-y", "@runapi.ai/ideogram-v3-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 an Ideogram V3 edit image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create an Ideogram V3 remix image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create an Ideogram V3 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 Ideogram V3 model and endpoint. |
Ideogram V3 covers 6 model variants across 3 endpoints. Each tool accepts the models listed for it:
Tool | Models |
|
|
|
|
|
|
Model availability can change between releases. Use check_pricing or the Ideogram V3 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 an Ideogram V3 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 Ideogram V3 pricing, then create the task if it matches my request.The assistant calls check_pricing and can link to the Ideogram V3 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 |
Ideogram V3 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 ideogram-v3 model line.
Inputs: model, action.
Create a Ideogram V3 task on RunAPI (edit image). Returns a task id, status, and output URLs.
Inputs: mask_url (required), source_image_url (required), seed, wait, +10 more.
Fetch the current status and latest result payload for a ideogram-v3 task.
Inputs: action (required), task_id (required).
Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
Inputs: force.
Create a Ideogram V3 task on RunAPI (remix image). Returns a task id, status, and output URLs.
Inputs: source_image_url (required), seed, wait, model, +14 more.
Create a Ideogram V3 task on RunAPI (text to image). Returns a task id, status, and output URLs.
Inputs: seed, wait, model, style, +10 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a clearly distinct role: three distinct image-generation modes (text_to_image, edit_image, remix_image), plus task polling (get_task), auth (login), and pricing (check_pricing). The three generation tools could look similar at a glance, but their mode-specific descriptions make the boundaries unambiguous.
Almost all tools follow a snake_case verb_noun pattern (check_pricing, edit_image, get_task, remix_image), which is predictable and readable. 'login' is a bare verb rather than verb_noun and 'text_to_image' inverts the pattern, but both are still clear and not confusing.
Six tools is well-scoped for an image-generation service: one auth, one pricing lookup, three generation modes, and one task-status retrieval. Each tool earns its place with no redundant or filler entries.
Core lifecycle is covered: authenticate, check cost, create tasks in all three modes, and poll task status with returned output URLs. Minor gaps exist (e.g. list tasks, cancel task), but agents can work around them since task ids and outputs are returned directly.
MCP server for Qwen Image 3 AI image generation
MCP server for Pixapi: check live credit pricing and balance, then generate images and video.
MCP server for Google Veo AI video generation
MCP server for Midjourney AI image generation and editing
