Modelflare

io.github.castaly-aiPublished by GitHub account castaly-aiv0.1.2Updated Oct 29, 2026

Image and video generation with one Modelflare Smart API Key.

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

Modelflare MCP server lets an assistant list, generate and edit images and create videos through a Modelflare Smart API Key, saving results locally.

What you can do
  • List the image, video and text models the API key can call, with links to each model's request contract
  • Generate images or edit existing ones with a chosen image model and save the output
  • Start asynchronous video tasks and return a task ID
  • Check a video task's status and progress
  • Download a finished video to the output directory, optionally waiting for it first
When to use it
Useful when you want an assistant inside Claude Desktop, Cursor, Gemini CLI or another MCP client to produce images or videos from prompts without switching tools, and you already have or are willing to open a Modelflare account with balance.
Requirements
Runs locally over stdio, typically via npx with the npm package. Requires a Modelflare Smart API Key in MODELFLARE_API_KEY. Optional MODELFLARE_BASE_URL (global, china or custom), MODELFLARE_OUTPUT_DIR for saved media, and MODELFLARE_LOCALE for error language. Network access to Modelflare and a funded account balance.
Before you install
Every generation is billed to your Modelflare balance by actual usage, so prompts can spend money; check usage logs and top-up status. The API key is a secret passed by environment variable. Generated files are written to the output directory, and result URLs expire, so downloads should happen soon after completion.

Installation

In SourceWeft

  1. Open Modelflare in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Modelflare MCP Server

Image and video generation for any MCP client — Claude Desktop, Cursor, Gemini CLI and more — with one Modelflare Smart API Key for every image and video model available to your account.

用一个 Modelflare Smart API Key,在任意 MCP 客户端里调用你账号可用的全部图像和视频模型。

mcp-name: io.github.castaly-ai/mcp-server

Get a Smart API Key / 获取 Smart API Key

  1. Sign up / 注册: https://modelflare.dev/sign-up?utm_source=mcp-registry&utm_medium=plugin&utm_campaign=integrations

  2. Console → API Keys → Create Smart API Key, and pick a routing strategy (Balanced / Stability first / Low price first).

    控制台 API Keys →「Create Smart API Key」,选择路由策略(均衡 / 稳定优先 / 低价优先)。

Configure / 配置

Add the server to your MCP client:

json
{  "mcpServers": {    "modelflare": {      "command": "npx",      "args": ["-y", "@modelflare/mcp-server"],      "env": {        "MODELFLARE_API_KEY": "<your Smart API Key>"      }    }  }}
VariableValue
MODELFLARE_API_KEYyour Smart API Key (required)
MODELFLARE_BASE_URLglobal → https://modelflare.dev/v1 (default) · china → https://origin.modelflare.dev/v1 · or a custom URL
MODELFLARE_OUTPUT_DIRwhere images and videos are saved (default ./modelflare-output)
MODELFLARE_LOCALEen (default) or zh for error messages

Claude Desktop: download modelflare-mcp-<version>.mcpb from Releases and open it; Claude Desktop asks for the API key, base URL and output folder. modelflare-mcp-<version>-smithery.mcpb is the same bundle with each tool's inputSchema in the manifest, as Smithery requires. node build-mcpb.mjs rebuilds both.

Tools / 工具

ToolWhat it does
list_modelsImage and video models your key can call, each with the docs page holding its exact request fields. kind: "text" lists text models.
generate_imageGenerates an image, or edits one with edit: true, and saves it. Gemini image models use generateContent; the others use the Images API.
create_videoStarts an asynchronous video task and returns its task ID.
get_video_statusStatus and progress of a video task.
download_videoSaves a finished video; can wait up to 300 seconds first.

Model-specific fields go in parameters (images) or request (videos) and are sent unchanged. The model list comes from your key, so new models appear without editing the key. Generated results are saved right away because result URLs expire.

Calls are billed to your Modelflare balance by actual usage; see https://modelflare.dev/usage-logs.

Troubleshooting / 常见问题

  • 401: the key is missing or invalid. Create a Smart API Key at https://modelflare.dev/keys.
  • model_not_found: a regular key only calls the models of its own group. A Smart API Key calls every model available to your account. If you already use a Smart API Key, that model is not available to your account right now.
  • 403 insufficient_user_quota: top up at https://modelflare.dev/billing.

Links

Docs: https://docs.modelflare.dev/ · Pricing: https://modelflare.dev/pricing

Listed on the M8ven MCP Trust Index.

License

MIT © Havenbyte LLC

Source: README.md at commit c99ab6e

Tools

5

list_models

List Modelflare models

Lists the models this Modelflare API key can call, with the docs page that holds each media model's exact request contract. Defaults to image and video models.

Parameterskind

generate_image

Generate or edit an image

Generates an image, or edits one with edit=true, using a Modelflare image model, and saves the result to the output directory. Billed to the Modelflare balance by actual usage.

Parameterseditmodelrequiredpromptrequiredparameters

create_video

Create a video task

Starts an asynchronous Modelflare video task and returns its task ID. Poll with get_video_status and save with download_video. Billed to the Modelflare balance by actual usage.

Parametersmodelrequiredrequestrequired

get_video_status

Get video task status

Returns the status and progress of a Modelflare video task.

Parameterstask_idrequired

download_video

Download a finished video

Saves a completed Modelflare video to the output directory. Optionally waits for the task first. Result URLs expire, so download soon after completion.

Parameterstask_idrequiredwait_seconds

Version history

2
  1. v0.1.2LatestOct 23, 2026
  2. v0.1.1Oct 14, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts