Skip to main content
Glama
AI Video Generator MCP Server

AI Video Generator MCP Server

by el-el-san

AI Video Generator MCP Server

This MCP (Model Context Protocol) server provides tools to generate videos from text prompts and images using AI image generation models.

Compatible Models

  • Luma Ray2 Flash - Luma's cutting edge image to video conversion model

  • Kling v1.6 Pro - Kling's high quality image to video conversion model

Related MCP server: Video Edit MCP Server

function

  • Video generation from text prompts

  • Video generation with start and/or end images

  • Control video parameters (aspect ratio, resolution, duration, loop)

  • Check the generation status

  • Choosing which AI model to use

install

  1. Clone this repository

  2. Install the dependencies:

    npm install
  3. Create a .env file and set your FAL.AI API key:

    FAL_KEY=your_fal_key_here

    You can get the API key from FAL.AI

Building the Server

npm run build

Running the Server

You can run the server directly:

npm start

Integration with Claude Desktop

To use this server with Claude Desktop, add the following to your claude_desktop_config.json file:

{
  "mcpServers": {
    "video-generator": {
      "command": "node",
      "args": ["your_install_path/fal-mcp-server/build/index.js"],
      "env": {
        "FAL_KEY": "your_fal_key_here"
      }
    }
  }
}

Available Tools

generate-video

It uses AI models to generate videos from text prompts and/or images.

Parameters:

  • prompt (required): A text description of the content of the video you want to generate.

  • image_url (optional): The starting image URL for the video (URL or base64 data URI).

  • end_image_url (optional): The end image URL for the video (URL or base64 data URI).

  • aspect_ratio (default "16:9"): Video aspect ratio ("16:9", "9:16", "4:3", "3:4", "21:9", "9:21")

  • resolution (default "540p"): Video resolution ("540p", "720p", "1080p")

  • duration (default "5s"): video length ("5s", "9s")

  • loop (default false): whether the video should loop

  • model (default "luma"): AI model to use ("luma"=Ray2, "kling"=Kling v1.6 Pro)

check-video-status

Check the status of your video generation request.

Parameters:

  • request_id (required): The request ID to check.

  • model (default "luma"): AI model used for the request ("luma"=Ray2, "kling"=Kling v1.6 Pro)

Claude usage example

猫が毛糸玉で遊んでいる動画を生成してください。縦向きモードでお願いします。Klingモデルを使用してください。

Claude calls the generate-video tool with the appropriate parameters and provides the resulting video URL.

Compare Models

  • Luma Ray2 Flash : Excellent for smooth motion and realistic physics, producing natural results.

  • Kling v1.6 Pro : Excellent for detailed textures and special effects, producing stylized results.

Depending on the prompt and the desired outcome, different models may work best.

Limitations

  • Video generation may take some time (especially at higher resolutions)

  • A valid FAL.AI API key and sufficient credits are required

  • Higher resolution and longer videos cost more credits

  • Both models consume FAL.AI credits (prices may vary per model)

troubleshooting

API Key Error

Make sure the FAL_KEY environment variable is set correctly, or you can set it directly in the Claude Desktop configuration file.

Video Generation Error

If an error occurs during video generation, a detailed error message will be logged. Common issues are:

  • Invalid or expired API key

  • Insufficient credits on your account

  • Inappropriate prompts or images

  • A temporary server-side issue

If the error persists, wait a while and try again or try changing the prompt.

license

MIT

Available Tools

2 tools
check-video-statusC

Check the status of a video generation request

Inputs: request_id (required), model.

generate-videoB

Generate a video from text prompt and/or images using AI models (Luma or Kling)

Inputs: prompt (required), aspect_ratio, duration, end_image_url, +4 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have completely distinct purposes with no overlap: one checks status of existing requests, the other creates new videos. An agent would never confuse these functions as they operate on different stages of the video generation workflow.

    Naming Consistency5/5

    Both tools follow a consistent verb-object naming pattern with hyphen separation: 'check-video-status' and 'generate-video'. The naming is predictable and follows the same convention throughout the set.

    Tool Count2/5

    With only 2 tools for a video generation server, the surface feels severely limited. While the basic create+status pair covers minimal functionality, a video generation domain typically requires more operations like listing videos, canceling generations, or managing templates. The count is too low for the apparent scope.

    Completeness2/5

    The toolset provides only generation initiation and status checking, creating significant gaps. Missing are operations like listing existing videos, canceling pending generations, retrieving generated content, managing templates/presets, or configuring generation parameters. Agents will hit dead ends when trying to manage the video lifecycle beyond initial creation.

    Related MCP Connectors

    Related MCP Servers