Skip to main content
Glama
enesjakozh
el-el-san

AI Video Generator MCP Server

by el-el-san
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

AI 视频生成器 MCP 服务器

该 MCP（模型上下文协议）服务器提供使用 AI 图像生成模型从文本提示和图像生成视频的工具。

兼容型号

  • Luma Ray2 Flash - Luma 的尖端图像到视频转换模型

  • Kling v1.6 Pro - Kling 的高质量图像到视频转换模型

Related MCP server: Video Edit MCP Server

功能

  • 根据文本提示生成视频

  • 带有开始和/或结束图像的视频生成

  • 控制视频参数（宽高比、分辨率、时长、循环）

  • 检查生成状态

  • 选择要使用的 AI 模型

安装

  1. 克隆此存储库

  2. 安装依赖项：

    npm install

  3. 创建一个.env文件并设置您的 FAL.AI API 密钥：

    FAL_KEY=your_fal_key_here

    您可以从FAL.AI获取 API 密钥

构建服务器

npm run build

运行服务器

您可以直接运行服务器：

npm start

与 Claude Desktop 集成

要将此服务器与 Claude Desktop 一起使用，请将以下内容添加到您的claude_desktop_config.json文件中：

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

可用工具

生成视频

它使用人工智能模型根据文本提示和/或图像生成视频。

参数：

  • prompt （必需）：要生成的视频内容的文本描述。

  • image_url （可选）：视频的起始图像 URL（URL 或 base64 数据 URI）。

  • end_image_url （可选）：视频的结束图像 URL（URL 或 base64 数据 URI）。

  • aspect_ratio （默认“16：9”）：视频纵横比（“16：9”，“9：16”，“4：3”，“3：4”，“21：9”，“9：21”）

  • resolution （默认“540p”）：视频分辨率（“540p”，“720p”，“1080p”）

  • duration （默认“5s”）：视频长度（“5s”，“9s”）

  • loop （默认 false）：视频是否循环播放

  • model （默认“luma”）：要使用的 AI 模型（“luma”=Ray2，“kling”=Kling v1.6 Pro）

检查视频状态

检查您的视频生成请求的状态。

参数：

  • request_id （必需）：要检查的请求 ID。

  • model （默认“luma”）：用于请求的 AI 模型（“luma”=Ray2，“kling”=Kling v1.6 Pro）

Claude 使用示例

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 使用适当的参数调用generate-video工具并提供生成的视频 URL。

比较型号

  • Luma Ray2 Flash ：非常适合平滑的动作和逼真的物理效果，可产生自然的效果。

  • Kling v1.6 Pro ：非常适合细节纹理和特殊效果，可产生风格化的效果。

根据提示和期望结果，不同的模型可能会发挥最佳作用。

限制

  • 视频生成可能需要一些时间（特别是在较高分辨率下）

  • 需要有效的 FAL.AI API 密钥和足够的积分

  • 分辨率更高、视频时间更长，需要消耗更多积分

  • 两种型号均消耗 FAL.AI 积分（价格可能因型号而异）

故障排除

API 密钥错误

验证 FAL_KEY 环境变量是否设置正确。也可以直接在Claude Desktop配置文件中设置。

视频生成错误

如果在视频生成过程中发生错误，则会记录详细的错误消息。常见问题有：

  • API 密钥无效或已过期

  • 您的账户余额不足

  • 不适当的提示或图像

  • 暂时的服务器端问题

如果错误仍然存在，请等待一段时间并重试或尝试更改提示。

执照

麻省理工学院

Available Tools

2 tools
check-video-statusC

Check the status of a video generation request

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoAI model used for the request (luma=Ray2, kling=Kling)luma
request_idYesThe request ID to check

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but reveals nothing about response format, error conditions, rate limits, authentication requirements, or whether this is a read-only operation (though implied by 'check'). For a status-checking tool with zero annotation coverage, this leaves significant behavioral gaps.

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, efficient sentence that states the core purpose without any wasted words. It's appropriately sized and front-loaded with the essential information.

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 status-checking tool with no annotations and no output schema, the description is incomplete. It doesn't explain what status information will be returned, possible states (pending, completed, failed), or how to interpret results. The agent would need to guess about the tool's behavior and output format.

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 the schema already fully documents both parameters. The description doesn't add any parameter semantics beyond what's in the schema (like explaining the relationship between request_id and previous video generation). Baseline 3 is appropriate when the schema does all the parameter documentation work.

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 clearly states the action ('check') and resource ('video generation request'), making the purpose immediately understandable. However, it doesn't differentiate this status-checking tool from its sibling 'generate-video' tool, which would be helpful for an agent choosing between them.

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 versus alternatives. There's no mention of prerequisites (like needing a request_id from a previous generation), nor does it explain the relationship with the sibling 'generate-video' tool, leaving the agent to infer usage context.

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

generate-videoB

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

ParametersJSON Schema
NameRequiredDescriptionDefault
aspect_ratioNoAspect ratio of the video16:9
durationNoDuration of the video (9s costs 2x more)5s
end_image_urlNoFinal image to end the video with (URL or base64 data URI)
image_urlNoInitial image to start the video from (URL or base64 data URI)
loopNoWhether the video should loop (blend end with beginning)
modelNoAI model to use (luma=Ray2, kling=Kling)luma
promptYesText description of the desired video content
resolutionNoResolution of the video (higher resolutions use more credits)540p

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions AI models but doesn't disclose important behavioral traits like: whether this is a synchronous or asynchronous operation, what permissions or authentication are needed, rate limits, credit costs (beyond the hint in the duration parameter schema), or what the output looks like. The description is minimal and lacks crucial operational context.

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, efficient sentence that states the core purpose without unnecessary words. It's appropriately sized and front-loaded with the essential information. Every word earns its place in this concise formulation.

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 complex video generation tool with 8 parameters and no annotations or output schema, the description is insufficient. It doesn't explain the operation's nature (async/sync), authentication requirements, cost implications beyond the duration hint, error conditions, or what happens after invocation. The combination of complexity and lack of structured metadata demands more comprehensive description.

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 the schema already documents all 8 parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema. The baseline score of 3 reflects adequate coverage through the schema alone, but the description doesn't enhance understanding of parameter usage or relationships.

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 clearly states the tool's purpose: 'Generate a video from text prompt and/or images using AI models (Luma or Kling)'. It specifies the verb ('generate'), resource ('video'), and input sources ('text prompt and/or images'), but doesn't differentiate from its sibling tool 'check-video-status' beyond the obvious generation vs. status check distinction.

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 context by mentioning AI models (Luma or Kling), suggesting this is for AI-generated video creation. However, it doesn't provide explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. The sibling tool 'check-video-status' is clearly complementary rather than an alternative.

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. 2 tool updatesv1.0.0
    • First observedcheck-video-status
    • First observedgenerate-video
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

B3.1/5.0

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.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches