What can you do with this server?

This MCP server provides focused access to RunAPI's Flux Kontext image generation API, enabling AI agents to create images, monitor tasks, and check pricing. * Generate images from text (text_to_image): Submit a prompt to create an image using flux-kontext-max or flux-kontext-pro, with options for: * Aspect ratio (21:9, 16:9, 4:3, 1:1, 3:4, 9:16) and output format (jpeg or png) * Source image URL for image-to-image generation * Wait for completion or return immediately with a task ID * Additional options: watermark, safety tolerance, prompt expansion, translation, callback URL, and polling interval * Check task status (get_task): Retrieve the current status and result payload (including output URLs) for a previously submitted task using its task ID. * Look up pricing (check_pricing): Query current pricing for Flux Kontext models and endpoints — no API key required, useful for cost checks before submitting a task.

How do I use @runapi.ai/flux-kontext-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/flux-kontext-mcp generate an image of a cat in space using flux-kontext-max" 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/flux-kontext-mcp

by runapi-ai

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Why This Package?

@runapi.ai/flux-kontext-mcp is a focused Model Context Protocol server for the Flux Kontext model line on RunAPI. It gives MCP-compatible assistants direct access to 1 endpoint and 2 model variants without loading the full RunAPI catalog.

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

Related MCP server: Image Generation MCP Server

Install

Add it to Claude Code:

claude mcp add flux-kontext -s user -- npx -y @runapi.ai/flux-kontext-mcp

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

claude mcp add flux-kontext -s project -- npx -y @runapi.ai/flux-kontext-mcp

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

{
  "mcpServers": {
    "flux-kontext": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/flux-kontext-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 Flux Kontext 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 Flux Kontext model and endpoint.

Models

Flux Kontext covers 2 model variants across 1 endpoint. Each tool accepts the models listed for it:

Tool	Models
`text_to_image`	`flux-kontext-max`, `flux-kontext-pro`

Model availability can change between releases. Use check_pricing or the Flux Kontext 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 Flux Kontext 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 Flux Kontext pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the Flux Kontext 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
Flux Kontext model page	https://runapi.ai/models/flux-kontext
npm package	@runapi.ai/flux-kontext-mcp
GitHub repository	runapi-ai/flux-kontext-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_pricingB

Look up RunAPI pricing for the flux-kontext 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

B3.3/5.0

Behavior2/5

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

With no annotations, the description carries the full burden. It only says 'look up' implying a read operation, but no details on permissions, side effects, or return behavior are given. The minimal description does not disclose behavioral traits beyond the name.

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, front-loaded sentence with no extraneous information. Every word contributes to the purpose.

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?

The description is minimal and does not explain default parameter behavior or output format. While the schema covers parameters, the tool description lacks completeness for a simple lookup without annotations or output schema.

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% with parameter descriptions already present. The tool description does not add any information about parameters beyond the schema, so a baseline of 3 is appropriate.

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: 'Look up RunAPI pricing for the flux-kontext model line.' It specifies the action (look up) and resource (pricing) and distinguishes from siblings like get_task and text_to_image.

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?

The description provides no guidance on when to use this tool vs alternatives, nor does it mention prerequisites or context. It merely states what it does, leaving the agent without context for selection.

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 flux-kontext 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

A3.8/5.0

Behavior3/5

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

No annotations provided; description does not state it is a read-only operation or any constraints. 'Fetch' implies non-destructive behavior, but explicit mention would raise confidence.

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?

Single, well-formed sentence with no redundant words. Front-loaded with key action and resource.

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?

With simple params and no output schema, the description provides essential info (status + payload) but could specify the response structure or default behavior of the 'action' param.

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% with descriptions for both parameters. The description does not add additional meaning beyond the schema, so baseline score 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 uses a specific verb ('Fetch') and resource ('task'), clearly indicating it retrieves status and result. It distinguishes from sibling tools like text_to_image (creation) and login/check_pricing.

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?

No explicit when-to-use or when-not-to-use guidance is given, but it's implied via context from sibling tool names. Could be improved by noting it should be called after creating a task via text_to_image.

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 Flux Kontext 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`	Yes	Image description (English only).
`watermark`	No	Watermark identifier.
`timeout_ms`	No
`aspect_ratio`	No	Output aspect ratio. Default: 16:9.
`callback_url`	No	Webhook URL for async notifications.
`output_format`	No	Output format. Default: jpeg.
`poll_interval_ms`	No
`safety_tolerance`	No	Content safety threshold. 0-6 for generation, 0-2 for editing. Default: 2.
`source_image_url`	No	Source image URL for editing mode.
`enable_translation`	No	Auto-translate non-English prompts. Default: true.
`enable_prompt_expansion`	No	Expand the prompt with more detail. Default: false.

TDQS

B3.3/5.0

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, but it only says it creates a task and returns an id, status, and output URLs. It does not disclose that wait defaults to true and the call polls until terminal, that callback_url enables webhooks, or that source_image_url switches the operation from text-to-image to image editing.

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?

One sentence with no filler: it front-loads the action, names the resource, and lists key return values. It is concise and well-structured, though it sacrifices the additional context that a more complex tool would benefit from.

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

Completeness2/5

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

For a 13-parameter asynchronous task API with polling, webhook callbacks, safety controls, translation, prompt expansion, and an editing mode, a one-line description is not complete. There is no output schema to fill the gap, and key orchestrational choices like default wait behavior and using get_task for later retrieval are absent.

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 85%, so the schema already documents 11 of 13 parameters; the description adds no per-parameter information beyond the general return shape. The two unclearly documented numeric parameters, timeout_ms and poll_interval_ms, are not clarified, but the high schema coverage justifies the baseline 3.

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 opens with the specific verb 'Create' and names the exact resource 'Flux Kontext task on RunAPI', then clarifies the use case with '(text to image)'. This clearly separates it from siblings like get_task, check_pricing, and login, which concern retrieval, pricing, and auth respectively.

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 use for generating a text-to-image task, but it does not state when to prefer this over get_task for polling/retrieving results. It also does not mention that providing source_image_url can invoke an editing mode, so the usage context is only partially implied.

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.

1 tool updatev0.1.13Sep 22, 2026

Changedtext_to_image9 fields changed

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / aspect_ratio / anyOf

Added value: +[
+  {
+    "const": "21:9",
+    "type": "string"
+  },
+  {
+    "const": "16:9",
+    "type": "string"
+  },
+  {
+    "const": "4:3",
+    "type": "string"
+  },
+  {
+    "const": "1:1",
+    "type": "string"
+  },
+  {
+    "const": "3:4",
+    "type": "string"
+  },
+  {
+    "const": "9:16",
+    "type": "string"
+  }
+]

removedInput schema / properties / aspect_ratio / enum

Removed value: -[
-  "21:9",
-  "16:9",
-  "4:3",
-  "1:1",
-  "3:4",
-  "9:16"
-]

removedInput schema / properties / aspect_ratio / type
```
Removed value: -"string"
```

addedInput schema / properties / output_format / anyOf

Added value: +[
+  {
+    "const": "jpeg",
+    "type": "string"
+  },
+  {
+    "const": "png",
+    "type": "string"
+  }
+]

removedInput schema / properties / output_format / enum
```
Removed value: -[
-  "jpeg",
-  "png"
-]
```
removedInput schema / properties / output_format / type
```
Removed value: -"string"
```
addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```

2 tool updatesv0.1.11Jul 29, 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_image9 fields changed
- addedInput schema / properties / aspect_ratio / description
```
Added value: +"Output aspect ratio. Default: 16:9."
```
- addedInput schema / properties / callback_url / description
```
Added value: +"Webhook URL for async notifications."
```
- addedInput schema / properties / enable_prompt_expansion / description
```
Added value: +"Expand the prompt with more detail. Default: false."
```
- addedInput schema / properties / enable_translation / description
```
Added value: +"Auto-translate non-English prompts. Default: true."
```
- addedInput schema / properties / output_format / description
```
Added value: +"Output format. Default: jpeg."
```
- addedInput schema / properties / prompt / description
```
Added value: +"Image description (English only)."
```
- addedInput schema / properties / safety_tolerance / description
```
Added value: +"Content safety threshold. 0-6 for generation, 0-2 for editing. Default: 2."
```
- addedInput schema / properties / source_image_url / description
```
Added value: +"Source image URL for editing mode."
```
- addedInput schema / properties / watermark / description
```
Added value: +"Watermark identifier."
```

1 tool updatev0.1.9Jul 13, 2026
- Addedlogin
2 tool updatesv0.1.2Jun 23, 2026
- Changedcheck_pricing1 field changed
  - changedInput schema / properties / action / description
```
Previous value: -"Endpoint name. Defaults to the line's primary endpoint."New value: +"Endpoint name. Defaults to the endpoint that offers the model."
```
- Changedtext_to_image5 fields changed
  - addedInput schema / properties / callback_url / type
```
Added value: +"string"
```
  - addedInput schema / properties / prompt / type
```
Added value: +"string"
```
  - addedInput schema / properties / source_image_url / type
```
Added value: +"string"
```
  - addedInput schema / properties / watermark / type
```
Added value: +"string"
```
  - addedInput schema / required
```
Added value: +[
+  "prompt"
+]
```
3 tool updatesv0.1.0Jun 19, 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

A3.8/5.0

Scored 2026-09-22 12:55 across 4 tools

Disambiguation5/5

Each tool has a distinct purpose: authentication, pricing lookup, task creation, and status retrieval. There is no overlap or ambiguity between the tools, allowing an agent to select the correct one without confusion.

Naming Consistency4/5

Tool names mostly follow a consistent snake_case verb_noun pattern (text_to_image, check_pricing, get_task). The 'login' tool is a single-word exception but is a common and recognizable auth action, so the overall consistency remains strong.

Tool Count5/5

With only 4 tools, the server is well-scoped for a focused flux-kontext image generation client. Each tool serves a necessary role (auth, pricing, creation, status) with no redundancy, making the count appropriate for the domain.

Completeness4/5

The essential workflow of authentication, task creation, and status retrieval is fully covered. Missing operations like cancel or listing past tasks are minor enhancements rather than critical gaps, so the surface is reasonably complete for primary use cases.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

mcp-flux-proOAuth
io.github.AceDataCloud
MCP server for Flux AI image generation
Image & Video Processing Multimedia Processing
23
FLUXOAuth
io.github.black-forest-labs
Official FLUX MCP server. Generate, edit, vary, and browse images from Black Forest Labs.
Image & Video Processing AI & Machine Learning
2
mcp-qwen-imageOAuth
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1
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

Related MCP Servers

flux-dev MCP Server
Agent Orchestration Autonomous Agents
nicekate
A
license
Not graded
quality
D
maintenance
Implements a Model Context Protocol (MCP) server powered by Flux API from Cephalon Cloud, enabling users to utilize advanced AI capabilities through standardized communication.
Updated 2 years ago (2025-02-19 07:01 UTC)
31
MIT
Image Generation MCP Server
Image & Video Processing Autonomous Agents
manascb1344
A
license
B
quality
D
maintenance
A Model Context Protocol server that enables high-quality image generation using the Flux.1 Schnell model via Together AI with customizable parameters.
Updated a year ago (2025-05-23 14:02 UTC)
1
33 npm
10
MIT
Flux Schnell MCP Server
Image & Video Processing Autonomous Agents
ckz
A
license
Not graded
quality
D
maintenance
A server that enables generating images through the Replicate API by calling the Flux Schnell model via the Model Context Protocol (MCP).
Updated 2 years ago (2025-03-10 19:24 UTC)
3
MIT
Flux Schnell Server
Image & Video Processing API Testing
m-mcp
F
license
B
quality
D
maintenance
An MCP image generation server based on the Flux Schnell model that provides API access for generating images from text prompts with customizable dimensions and seeds.
Updated a year ago (2025-05-29 09:05 UTC)
1
1
-