What can you do with this server?

This server provides focused access to GPT-4o Image generation capabilities on RunAPI, allowing AI agents to create, monitor, and price image generation tasks. * Generate images from text (text_to_image): Submit a text-to-image task using the gpt-4o-image model, with options to control aspect ratio (1:1, 3:2, 2:3), output count (1, 2, or 4 images), and whether to wait synchronously for results or return a task ID immediately for later polling. * Poll task status (get_task): Fetch the current status and result payload (including output URLs) for a previously created image generation task using its task ID. * Check pricing (check_pricing): Look up the current pricing snapshot for the gpt-4o-image model and its text_to_image endpoint — no API key required. The server is compatible with any MCP host (Claude Code, Cursor, Windsurf, VS Code, etc.) via stdio configuration.

How do I use @runapi.ai/gpt-4o-image-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@runapi.ai/gpt-4o-image-mcp Generate an image of a cat wearing a wizard hat" 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/gpt-4o-image-mcp

Official

by runapi-ai

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Why This Package?

@runapi.ai/gpt-4o-image-mcp is a focused Model Context Protocol server for the GPT-4o Image model line on RunAPI. It gives MCP-compatible assistants direct access to 1 endpoint and 1 model variant without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to GPT-4o Image. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.

Related MCP server: @runapi.ai/gpt-image-2-mcp

Install

Add it to Claude Code:

claude mcp add gpt-4o-image -s user -- npx -y @runapi.ai/gpt-4o-image-mcp

Use project scope when the server should be shared with a repository:

claude mcp add gpt-4o-image -s project -- npx -y @runapi.ai/gpt-4o-image-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

{
  "mcpServers": {
    "gpt-4o-image": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/gpt-4o-image-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
`text_to_image`	Yes	Create a GPT-4o Image text to image task and optionally wait for a terminal status. Returns the task id, status, and output URLs.
`get_task`	Yes	Fetch the current status and latest payload for an existing task.
`check_pricing`	No	Look up current pricing for a GPT-4o Image model and endpoint.

Models

GPT-4o Image covers 1 model variant across 1 endpoint. Each tool accepts the models listed for it:

Tool	Models
`text_to_image`	`gpt-4o-image`

Model availability can change between releases. Use check_pricing or the GPT-4o Image 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 a GPT-4o Image text to image task with RunAPI.

The assistant can call check_pricing, then text_to_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 GPT-4o Image pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the GPT-4o Image model page for the canonical catalog entry.

Configuration

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.

Links

Resource	URL
GPT-4o Image model page	https://runapi.ai/models/gpt-4o-image
npm package	@runapi.ai/gpt-4o-image-mcp
GitHub repository	runapi-ai/gpt-4o-image-mcp
RunAPI MCP overview	runapi.ai/mcp
RunAPI docs	runapi.ai/docs

License

Licensed under the Apache License, Version 2.0.

Available Tools

4 tools

check_pricingC

Look up RunAPI pricing for the gpt-4o-image model line.

ParametersJSON Schema

Name	Required	Description	Default
`model`	No	Model slug. Defaults to the line's primary model.
`action`	No	Endpoint name. Defaults to the endpoint that offers the model.

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. It never states that this is a read-only/no-side-effect operation, whether it consumes credits, or what the response contains, and it hardcodes 'gpt-4o-image' even though the schema lets the caller pass any model slug.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single efficient sentence with the resource front-loaded and zero filler. It is arguably under-specified rather than padded, so length is not the problem.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-required-parameter lookup with no output schema and no annotations, the agent can invoke it, but it gets no picture of what pricing data is returned or how it is shaped. Adequate but with a clear gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the model and action parameters are already fully documented with defaults, making the baseline 3 appropriate. The description adds no syntax, format, or defaulting detail beyond the schema and arguably narrows the model scope more than the schema does.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (look up) and resource (RunAPI pricing) scoped to a named model line, which is clearly distinct from the siblings text_to_image, get_task, and login. It stops short of explicitly contrasting itself with any sibling, but no plausible confusion exists.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this versus text_to_image (e.g., 'check cost before invoking generation') and no prerequisites or exclusions. The use case is only loosely implied by the word 'pricing'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_taskA

Fetch the current status and latest result payload for a gpt-4o-image task.

ParametersJSON Schema

Name	Required	Description	Default
`action`	No	Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint.
`task_id`	Yes	Task id returned when the task was created.

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully signals a read-only retrieval that returns 'current status' plus the 'latest result payload' (implying results may be partial), but omits terminal-state semantics, polling behavior, and auth/permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the resource and scope are stated immediately and nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity 2-param fetch with no output schema, the description does convey what comes back (status and latest payload). However, without annotations or an output schema it should say more about result states and polling expectations to be fully self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both task_id and the action enum/default are already documented in the schema. The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Fetch') and names the exact resource ('current status and latest result payload') scoped to a gpt-4o-image task. It is clearly distinct from text_to_image, check_pricing, and login, though it never explicitly contrasts itself with the creation sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the polling/retrieval counterpart to an async text_to_image call. There is no explicit statement of when to call it (e.g., after task creation, on what cadence) or what alternatives exist.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

loginA

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

ParametersJSON Schema

Name	Required	Description	Default
`force`	No	Re-run browser login when the current credential comes from the local config file.

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It discloses the interactive browser flow and the file write side effect (config.json). However, it does not mention that it may overwrite existing credentials or that it could block waiting for user input, though these are implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the action ('Authenticate RunAPI') and provides necessary details without extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple login tool with one optional parameter and no output schema, the description covers the core purpose and side effect. It lacks an explicit statement that this is a prerequisite for other tools, but that is implied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the only parameter 'force' has a description). The tool description adds no additional meaning about parameters beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Authenticate'), target resource ('RunAPI'), method ('browser PKCE login flow'), and side effect (saving to config.json). It is distinct from sibling tools, none of which relate to authentication.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (to authenticate RunAPI) but does not explicitly say when to run it (e.g., before other RunAPI tools) or when to use the 'force' parameter. Since there are no alternative auth tools among siblings, 'vs alternatives' is not applicable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

text_to_imageB

Create a GPT-4o Image task on RunAPI (text to image). Returns a task id, status, and output URLs.

ParametersJSON Schema

Name	Required	Description
`wait`	No	Poll until the task reaches a terminal status.
`model`	No	RunAPI model slug for this model line.
`prompt`	No	Declared type: string.
`mask_url`	No	Declared type: string.
`timeout_ms`	No
`aspect_ratio`	Yes	Declared type: string. Known values: "1:1", "3:2", "2:3".
`callback_url`	No	Declared type: string.
`output_count`	No	Declared type: integer. Known values: 1, 2, 4.
`poll_interval_ms`	No
`source_image_urls`	No	Declared type: array.
`enable_prompt_expansion`	No	Declared type: boolean.

TDQS

B3.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it partially delivers by disclosing the return shape (task id, status, output URLs), which is genuinely useful since no output schema exists. However, it says nothing about the asynchronous nature of the task, how the 'wait' and 'callback_url' parameters change blocking behavior, or any auth/rate-limit constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the action front-loaded and the return contract second. Nothing is wasted and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with no annotations and no output schema, the description covers the action and the return payload but omits the operational semantics that matter most: that this enqueues an async task, and how 'wait', 'timeout_ms', and 'callback_url' interact. Adequate but noticeably incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 82%, so the baseline is 3. The description adds no parameter-level meaning at all, and several schema descriptions are just 'Declared type: string' filler, so the agent gets no extra help on prompt, mask_url, or callback_url semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('Create a GPT-4o Image task on RunAPI') and disambiguates the modality with '(text to image)', which separates it from siblings like get_task and check_pricing. It stops short of explicitly naming an alternative for retrieval, but the action is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites, and no indication of how this relates to get_task for checking results or to login for authentication. The agent must infer the entire workflow from the sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

3 tool updatesv0.2.0Oct 5, 2026
- Changedcheck_pricing2 fields changed
  - removedInput schema / additionalProperties
```
Removed value: -false
```
  - removedInput schema / properties / model / enum
```
Removed value: -[
-  "gpt-4o-image"
-]
```
- Changedget_task1 field changed
  - removedInput schema / additionalProperties
```
Removed value: -false
```
- Changedtext_to_image15 fields changed
  - changedInput schema / additionalProperties
```
Previous value: -falseNew value: +{}
```
  - addedInput schema / properties / aspect_ratio / description
```
Added value: +"Declared type: string. Known values: \"1:1\", \"3:2\", \"2:3\"."
```
  - removedInput schema / properties / aspect_ratio / enum
```
Removed value: -[
-  "1:1",
-  "3:2",
-  "2:3"
-]
```
  - addedInput schema / properties / callback_url / description
```
Added value: +"Declared type: string."
```
  - addedInput schema / properties / enable_prompt_expansion / description
```
Added value: +"Declared type: boolean."
```
  - addedInput schema / properties / mask_url / description
```
Added value: +"Declared type: string."
```
  - removedInput schema / properties / model / enum
```
Removed value: -[
-  "gpt-4o-image"
-]
```
  - addedInput schema / properties / output_count / description
```
Added value: +"Declared type: integer. Known values: 1, 2, 4."
```
  - removedInput schema / properties / output_count / enum
```
Removed value: -[
-  1,
-  2,
-  4
-]
```
  - changedInput schema / properties / output_count / type
```
Previous value: -"number"New value: +"integer"
```
  - addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
  - addedInput schema / properties / prompt / description
```
Added value: +"Declared type: string."
```
  - addedInput schema / properties / source_image_urls / description
```
Added value: +"Declared type: array."
```
  - removedInput schema / properties / source_image_urls / maxItems
```
Removed value: -5
```
  - addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```

2 tool updatesv0.1.7Jul 22, 2026

Changedget_task1 field changed

changedInput schema / properties / action / description

Previous value: -"Endpoint the task was created on. Defaults to the line's only endpoint."New value: +"Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint."

Changedtext_to_image5 fields changed
- addedInput schema / properties / callback_url
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / enable_prompt_expansion
```
Added value: +{
+  "type": "boolean"
+}
```
- addedInput schema / properties / mask_url
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / prompt
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / source_image_urls
```
Added value: +{
+  "items": {},
+  "maxItems": 5,
+  "type": "array"
+}
```

1 tool updatev0.1.6Jul 13, 2026
- Addedlogin
3 tool updatesv0.1.0Jun 24, 2026
- First observedcheck_pricing
- First observedget_task
- First observedtext_to_image

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored 2026-10-05 07:40 across 4 tools

Disambiguation5/5

Each tool targets a distinct action: text_to_image creates a generation task, get_task polls status/result, check_pricing is a read-only info lookup, and login handles auth. There is no overlap and an agent can trivially tell them apart.

Naming Consistency4/5

text_to_image, get_task, and check_pricing roughly follow a verb/noun style, while login is a bare verb. Mostly consistent with one minor deviation.

Tool Count4/5

Four tools is a reasonable, well-scoped set for a single-model image service: one generation, one polling, plus pricing and auth support. It is slightly thin but nothing is redundant.

Completeness3/5

The core create-and-poll workflow is covered, but the surface lacks common image operations such as image-to-image/editing, variations, listing tasks, or cancellation. These are notable gaps for a GPT-4o image line.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

OpenAI Tools MCP Server B
ai.com.mcp
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Image & Video Processing Audio Processing Multimedia Processing
927
PixapiOAuth
io.github.Pixapi-AI
MCP server for Pixapi: check live credit pricing and balance, then generate images and video.
Image & Video Processing AI & Machine Learning
1
mcp-qwen-imageOAuth
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1
mcp-openaiOAuth
io.github.AceDataCloud
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
AI & Machine Learning Image & Video Processing
11

Related MCP Servers

@runapi.ai/gemini-omni-mcp
AI & Machine Learning Multimedia Processing
runapi-ai
A
license
A
quality
A
maintenance
MCP server for the Gemini Omni model line, enabling task creation (audio, character, text-to-video) and pricing checks through RunAPI.
Updated 8 days ago (2026-09-30 11:30 UTC)
6
289 npm
Apache 2.0
@runapi.ai/gpt-image-2-mcpofficial
Image & Video Processing AI & Machine Learning
runapi-ai
A
license
A
quality
A
maintenance
An MCP server that enables AI image editing and generation using the GPT Image 2 model line via RunAPI, with task polling and pricing checks.
Updated 8 days ago (2026-09-30 11:30 UTC)
5
287 npm
Apache 2.0
Ideogram V3 MCP Server
AI & Machine Learning Image & Video Processing
runapi-ai
A
license
A
quality
A
maintenance
MCP server for Ideogram V3 model line enabling image editing, reframing, remixing, and text-to-image generation with task polling and pricing checks through RunAPI.
Updated 8 days ago (2026-09-30 11:34 UTC)
7
251 npm
Apache 2.0
imagen-4-mcp
AI & Machine Learning Image & Video Processing
runapi-ai
A
license
A
quality
A
maintenance
RunAPI MCP server for the Imagen 4 model line. Create tasks, poll their status, and check pricing through a single RunAPI API key.
Updated 8 days ago (2026-09-30 11:34 UTC)
5
254 npm
Apache 2.0

Why This Package?

Install

Tools

Models

Agent Prompts

Create a task

Submit without waiting

Check pricing before creating

Configuration

Links

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

@runapi.ai/gpt-image-2-mcpofficial