Video Clip MCP
Provides video manipulation capabilities including video clipping, merging, and splitting through FFmpeg's processing engine, enabling precise time-based editing and format conversion.
Built on Node.js with specific version requirements (>=14.16.0), enabling cross-platform compatibility for the video processing tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Video Clip MCPclip the video from 0:15 to 1:30 and save as highlight.mp4"
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.
🎬 Video Clip MCP
📖 项目简介
基于 AI MCP 协议的专业视频剪辑工具,提供高效的视频处理能力和智能化操作体验。无需手动安装 FFmpeg,开箱即用!
Related MCP server: FFmpeg-MCP Server
✨ 核心功能
🎯 精准剪辑 - 支持毫秒级精度的视频片段裁剪
🔗 智能合并 - 多视频文件无缝拼接,自动适配格式差异
✂️ 灵活分割 - 按时长、大小或段数智能分割视频
📊 信息获取 - 详细的视频元数据分析和格式检测
🚀 批量处理 - 高效的批量任务管理和并行处理
🎨 多格式支持 - 支持主流视频格式和编码标准
📈 任务监控 - 实时任务状态跟踪和进度管理
🛠️ 高度可配置 - 丰富的编码参数和质量预设
📦 安装使用
全局安装(推荐)
npm install -g @pickstar-2002/video-clip-mcp@latest临时使用
npx @pickstar-2002/video-clip-mcp@latest🔧 MCP 服务器配置
Claude Desktop
在 claude_desktop_config.json 中添加:
{
"mcpServers": {
"video-clip": {
"command": "npx",
"args": ["@pickstar-2002/video-clip-mcp@latest"]
}
}
}Cursor AI
在 .cursorrules 或项目配置中添加:
{
"mcp": {
"servers": {
"video-clip": {
"command": "npx @pickstar-2002/video-clip-mcp@latest"
}
}
}
}WindSurf
在 windsurfconfig.json 中配置:
{
"mcpServers": {
"video-clip": {
"command": "npx",
"args": ["@pickstar-2002/video-clip-mcp@latest"],
"env": {}
}
}
}CodeBuddy
在项目根目录创建 .codebuddy/mcp.json:
{
"servers": {
"video-clip": {
"command": "npx @pickstar-2002/video-clip-mcp@latest",
"description": "🎬 视频剪辑处理工具"
}
}
}其他 MCP 兼容工具
通用配置格式:
{
"mcpServers": {
"video-clip": {
"command": "npx",
"args": ["@pickstar-2002/video-clip-mcp@latest"]
}
}
}💡 使用示例
基础视频剪辑
// 剪辑视频片段(10秒到30秒)
await clipVideo({
inputPath: "input.mp4",
outputPath: "output.mp4",
timeSegment: {
start: 10000, // 10秒(毫秒)
end: 30000 // 30秒(毫秒)
},
quality: "fast",
videoCodec: "libx264"
});视频合并
// 合并多个视频文件
await mergeVideos({
inputPaths: ["video1.mp4", "video2.mp4", "video3.mp4"],
outputPath: "merged.mp4",
quality: "medium",
resolution: { width: 1920, height: 1080 }
});视频分割
// 按时长分割视频
await splitVideo({
inputPath: "long_video.mp4",
outputDir: "./segments",
splitBy: "duration",
duration: 60, // 每60秒一段
namePattern: "segment_{index}.{ext}"
});批量处理
// 批量处理任务
const tasks = [
{
type: "clip",
options: {
inputPath: "video1.mp4",
outputPath: "clip1.mp4",
timeSegment: { start: 0, end: 30000 }
}
},
{
type: "clip",
options: {
inputPath: "video2.mp4",
outputPath: "clip2.mp4",
timeSegment: { start: 10000, end: 40000 }
}
}
];
await batchProcess({ tasks });🎥 支持格式
视频格式
输入格式: MP4, AVI, MOV, MKV, WebM, FLV, 3GP, WMV
输出格式: MP4, AVI, MOV, MKV, WebM
视频编码
H.264 (libx264) - 通用兼容性最佳
H.265 (libx265) - 高压缩比,文件更小
VP9 (libvpx-vp9) - 开源编码,适合网络传输
AV1 (libaom-av1) - 新一代编码,压缩效率极高
音频编码
AAC - 高质量音频编码
MP3 (libmp3lame) - 通用兼容性
Opus (libopus) - 低延迟高质量
Vorbis (libvorbis) - 开源音频编码
🖥️ 系统要求
Node.js 版本
最低要求: Node.js 18.0.0+
推荐版本: Node.js 20.0.0+
系统依赖
FFmpeg: 自动安装(通过 @ffmpeg-installer/ffmpeg 包)
操作系统: Windows 10+, macOS 10.15+, Linux (Ubuntu 18.04+)
推荐硬件配置
CPU: 4核心以上,支持硬件加速更佳
内存: 8GB RAM 以上
存储: SSD 硬盘,至少2GB可用空间
GPU: 支持硬件编码的显卡(可选)
📚 API 文档
核心接口定义
interface VideoClipOptions {
inputPath: string;
outputPath: string;
timeSegment: {
start: number; // 开始时间(毫秒)
end: number; // 结束时间(毫秒)
};
quality?: 'ultrafast' | 'fast' | 'medium' | 'slow' | 'veryslow';
videoCodec?: 'libx264' | 'libx265' | 'libvpx-vp9' | 'libaom-av1';
audioCodec?: 'aac' | 'libmp3lame' | 'libopus' | 'libvorbis';
preserveMetadata?: boolean;
}
interface MergeVideosOptions {
inputPaths: string[];
outputPath: string;
quality?: string;
videoCodec?: string;
audioCodec?: string;
resolution?: { width: number; height: number };
fps?: number;
}
interface SplitVideoOptions {
inputPath: string;
outputDir: string;
splitBy: 'duration' | 'size' | 'segments';
duration?: number; // 按时长分割(秒)
maxSize?: number; // 按大小分割(MB)
segmentCount?: number; // 分割段数
namePattern?: string; // 文件命名模式
}
interface VideoInfo {
duration: number; // 时长(秒)
width: number; // 宽度
height: number; // 高度
fps: number; // 帧率
bitrate: number; // 比特率
format: string; // 格式
codec: string; // 编码
size: number; // 文件大小(字节)
}
interface TaskStatus {
id: string;
type: 'clip' | 'merge' | 'split';
status: 'pending' | 'processing' | 'completed' | 'failed';
progress?: number;
createdAt: string;
completedAt?: string;
error?: string;
result?: any;
}主要方法
// 获取视频信息
getVideoInfo(filePath: string): Promise<VideoInfo>
// 剪辑视频
clipVideo(options: VideoClipOptions): Promise<string>
// 合并视频
mergeVideos(options: MergeVideosOptions): Promise<string>
// 分割视频
splitVideo(options: SplitVideoOptions): Promise<string[]>
// 批量处理
batchProcess(tasks: BatchTask[]): Promise<string[]>
// 获取任务状态
getTaskStatus(taskId: string): Promise<TaskStatus>
// 取消任务
cancelTask(taskId: string): Promise<boolean>
// 获取支持的格式
getSupportedFormats(): Promise<SupportedFormats>🚨 疑难解答
常见问题及解决方案
1. 🔄 Connection closed 错误
问题描述: 使用 npx 时出现连接关闭错误
解决方案(按推荐顺序):
a. 首选方案 - 使用 @latest 标签
npx @pickstar-2002/video-clip-mcp@latestb. 备用方案 - 锁定特定版本
npx @pickstar-2002/video-clip-mcp@1.2.0c. 终极方案 - 清理 npx 缓存
# Windows
npx clear-npx-cache
# 或者手动删除缓存目录
rmdir /s "%APPDATA%\npm-cache\_npx"
# macOS/Linux
npx clear-npx-cache
# 或者手动删除缓存目录
rm -rf ~/.npm/_npx2. 🎬 FFmpeg 相关错误
问题描述: FFmpeg 执行失败或找不到
解决方案:
本工具已内置 FFmpeg,无需手动安装
如果仍有问题,请检查网络连接(首次使用需下载 FFmpeg)
确保有足够的磁盘空间(至少 100MB)
3. 📁 文件路径问题
问题描述: 输入或输出文件路径错误
解决方案:
使用绝对路径而非相对路径
确保路径中不包含特殊字符
Windows 用户注意使用正斜杠
/或双反斜杠\\
4. 🔧 权限问题
问题描述: 没有文件读写权限
解决方案:
确保对输入文件有读取权限
确保对输出目录有写入权限
Windows 用户可能需要以管理员身份运行
5. 💾 内存不足
问题描述: 处理大文件时内存溢出
解决方案:
降低视频质量设置
分段处理大文件
增加系统虚拟内存
📞 获取帮助
如果以上解决方案无法解决您的问题,请:
📋 收集错误信息和系统环境
🐛 在 GitHub Issues 提交问题
💬 联系开发者(见下方联系方式)
🤝 贡献指南
我们欢迎所有形式的贡献!请遵循以下步骤:
Fork 本仓库
创建特性分支:
git checkout -b feature/amazing-feature提交更改:
git commit -m 'Add amazing feature'推送分支:
git push origin feature/amazing-feature提交 Pull Request
开发环境设置
# 克隆仓库
git clone https://github.com/pickstar-2002/video-clip-mcp.git
cd video-clip-mcp
# 安装依赖
npm install
# 构建项目
npm run build
# 启动开发模式
npm run dev📄 许可证
本项目采用 MIT License 开源协议。您可以自由使用、修改和分发本软件。
🙏 致谢
感谢以下开源项目和社区的支持:
FFmpeg - 强大的多媒体处理框架
fluent-ffmpeg - Node.js FFmpeg 封装库
Model Context Protocol - AI 工具集成协议
TypeScript - 类型安全的 JavaScript 超集
开源社区 - 所有贡献者和用户的支持
🌟 支持项目
如果这个项目对您有帮助,请:
⭐ 给项目点个 Star
🐛 报告问题和建议
🔄 分享给更多开发者
让我们一起打造更好的视频处理工具!🚀
📞 联系方式
微信: pickstar_loveXX
Available Tools
8 toolsbatchProcessC
批量处理视频任务
| Name | Required | Description | Default |
|---|---|---|---|
| tasks | Yes | 批量任务配置数组 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. The description only states '批量处理视频任务' without explaining what happens during processing, whether it's synchronous/asynchronous, if it returns status information, what errors might occur, or any rate limits. For a batch processing tool with no annotation coverage, this is completely inadequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with just one Chinese phrase ('批量处理视频任务'). While this may be too brief for completeness, as pure conciseness it's maximally efficient with zero wasted words. The single phrase is front-loaded with the core concept.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given this is a batch processing tool with no annotations, no output schema, and multiple sibling tools for individual operations, the description is insufficient. It doesn't explain the relationship to sibling tools, what the tool returns, how to monitor progress, or error handling. For a tool that presumably orchestrates multiple video operations, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 the single 'tasks' parameter with its structure. The description doesn't add any meaning beyond what the schema provides about task types or options. With high schema coverage, the baseline is 3 even without additional parameter information in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '批量处理视频任务' (batch process video tasks) states a general purpose but lacks specificity. It mentions 'video tasks' but doesn't clarify what types of tasks or distinguish from sibling tools like clipVideo, mergeVideos, and splitVideo which handle individual operations. The purpose is vague rather than specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, when batch processing is appropriate, or how it relates to sibling tools like clipVideo, mergeVideos, and splitVideo which handle similar operations individually. There's no explicit or implied usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
cancelTaskC
取消指定的处理任务
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | 任务ID |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states the action without behavioral details. It doesn't disclose if cancellation is reversible, requires specific permissions, affects other tasks, has rate limits, or what happens on success/failure (e.g., partial rollback). This is inadequate for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a simple tool and front-loaded with the core action, though it could benefit from more context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks crucial context like behavioral effects, error conditions, or return values. Given the server context (video processing tools), it should clarify what 'cancel' entails (e.g., stops processing, deletes partial files).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with one parameter ('taskId') documented in the schema. The description adds no additional meaning beyond implying 'taskId' identifies the task to cancel, which is already clear from the schema. Baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '取消指定的处理任务' clearly states the action (cancel) and target (specified processing task). It uses a specific verb and resource, though it doesn't explicitly differentiate from sibling tools like 'getTaskStatus' or 'batchProcess' which might involve task management.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention prerequisites (e.g., task must be running), exclusions (e.g., cannot cancel completed tasks), or refer to sibling tools like 'getTaskStatus' for checking task state before cancellation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
clipVideoC
剪辑视频片段,支持毫秒级精度的时间段裁剪
| Name | Required | Description | Default |
|---|---|---|---|
| inputPath | Yes | 输入视频文件路径 | |
| outputPath | Yes | 输出视频文件路径 | |
| timeSegment | Yes | ||
| quality | No | 视频质量预设 | |
| videoCodec | No | 视频编码格式 | |
| audioCodec | No | 音频编码格式 | |
| preserveMetadata | No | 是否保留元数据 |
TDQS
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 '毫秒级精度' (millisecond precision) which adds some context about accuracy, but doesn't describe important behavioral aspects: whether this is a destructive operation (modifies or creates new files), what happens if input/output paths are invalid, performance characteristics, error handling, or what the tool returns (since no output schema exists). The description is minimal and lacks critical operational details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise - just one sentence with 11 Chinese characters. It's front-loaded with the core purpose and includes one key feature (millisecond precision). There's no wasted language, though one could argue it's too brief given the tool's complexity. The structure is simple but effective for its length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a video processing tool with 7 parameters (including complex nested objects and enums), no annotations, and no output schema, the description is inadequate. It doesn't explain what the tool returns, error conditions, performance implications of quality/codec choices, or how it differs from similar video manipulation tools. The high parameter count and technical nature of video processing demand more contextual information than this minimal description provides.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high at 86%, so the schema already documents most parameters well. The description adds no parameter-specific information beyond what's in the schema - it doesn't explain the 'timeSegment' object structure, quality presets, codec choices, or metadata preservation implications. With high schema coverage, the baseline is 3, and the description doesn't enhance parameter understanding beyond the structured documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '剪辑视频片段' (clip video segments) with '毫秒级精度的时间段裁剪' (millisecond-precision time segment cropping). It specifies the verb (clip/crop) and resource (video segments) with precision details. However, it doesn't explicitly differentiate from sibling tools like 'splitVideo' or 'mergeVideos' which may have overlapping functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention sibling tools like 'splitVideo' (which might split at specific points rather than crop segments) or 'mergeVideos' (which combines videos). There's no context about prerequisites, limitations, or typical use cases for this specific clipping operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getSupportedFormatsB
获取支持的视频格式和编码
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what the tool does ('获取支持的视频格式和编码') without adding any context about traits like whether it's a read-only operation, if it requires authentication, rate limits, or what the return format might be. For a tool with zero annotation coverage, this is a significant gap in transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: '获取支持的视频格式和编码'. It is front-loaded with the core purpose, has zero wasted words, and is appropriately sized for a simple tool. Every part of the sentence earns its place by clearly stating the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is complete enough to convey the basic purpose. However, it lacks details on behavioral traits and usage guidelines, which are needed for full context. Since there's no output schema, the description doesn't explain return values, but that's acceptable given the tool's straightforward nature.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and the schema description coverage is 100% (as there are no parameters to describe). The description doesn't need to add parameter semantics, so it meets the baseline expectation. No additional information is required or provided, which is appropriate for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '获取支持的视频格式和编码' (Get supported video formats and encodings). It specifies the verb '获取' (get) and the resource '支持的视频格式和编码' (supported video formats and encodings), making the intent unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'getVideoInfo', which might also provide format-related information, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention any context, prerequisites, or exclusions, such as whether it should be used before processing videos or as a reference for other tools like 'clipVideo' or 'mergeVideos'. Without such information, users must infer usage from the purpose alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getTaskStatusC
获取任务状态
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | 任务ID |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. '获取任务状态' implies a read-only operation, but it doesn't specify if it requires authentication, has rate limits, returns real-time or cached data, or what happens with invalid task IDs. This leaves significant gaps for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single phrase ('获取任务状态'), which is highly concise and front-loaded with the core purpose. There's no wasted text, though it could benefit from slightly more detail to improve clarity without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the status return values might be (e.g., pending, completed, failed), error conditions, or how it fits with sibling tools like 'cancelTask'. For a status-checking tool in a video processing context, this leaves critical gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with 'taskId' documented as '任务ID' (task ID). The description adds no additional parameter semantics beyond this, but since the schema fully covers the single parameter, the baseline score of 3 is appropriate as the schema handles the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取任务状态' (Get task status) clearly states the verb ('get') and resource ('task status'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'getVideoInfo' or 'getSupportedFormats' which also retrieve information, leaving the scope somewhat vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention prerequisites (e.g., needing a task ID from another operation), exclusions, or comparisons to siblings like 'cancelTask' or 'batchProcess', leaving the agent without usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getVideoInfoC
获取视频文件的详细信息
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | 视频文件路径 |
TDQS
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 states what the tool does but doesn't describe how it behaves—such as whether it's read-only, what kind of information is returned, error handling, or performance characteristics. This leaves significant gaps for a tool that presumably reads and processes video metadata.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for a tool that likely returns complex video metadata. It doesn't hint at the structure or type of information returned (e.g., duration, resolution, codec), which could be critical for an agent to understand the tool's utility and integration into workflows.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'filePath' clearly documented in the schema as '视频文件路径' (video file path). The description doesn't add any additional meaning beyond this, such as format examples or constraints, but the schema provides adequate baseline information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('获取' meaning 'get') and resource ('视频文件的详细信息' meaning 'detailed information of video files'), making the purpose immediately understandable. It doesn't specifically distinguish from siblings like 'getTaskStatus' or 'getSupportedFormats', but the focus on video file details is reasonably clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, context for usage, or differentiate it from sibling tools like 'getTaskStatus' or 'getSupportedFormats', leaving the agent to infer appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
mergeVideosC
合并多个视频文件,支持不同格式和分辨率的智能适配
| Name | Required | Description | Default |
|---|---|---|---|
| inputPaths | Yes | 输入视频文件路径数组 | |
| outputPath | Yes | 输出视频文件路径 | |
| quality | No | 视频质量预设 | |
| videoCodec | No | 视频编码格式 | |
| audioCodec | No | 音频编码格式 | |
| resolution | No | 目标分辨率 | |
| fps | No | 目标帧率 |
TDQS
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 '智能适配' (intelligent adaptation) for formats and resolutions, hinting at automatic processing, but doesn't clarify critical behaviors: whether merging is destructive to source files, if it requires specific permissions, processing time expectations, error handling, or output format details. For a complex video processing tool with 7 parameters, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('合并多个视频文件') and adds a key feature ('支持不同格式和分辨率的智能适配'). There is zero wasted text, and it's appropriately sized for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 parameters, video processing with potential side effects), lack of annotations, and no output schema, the description is incomplete. It doesn't address what the tool returns (e.g., success status, error messages), behavioral nuances like file overwriting or resource usage, or how it differs from siblings. For a mutation tool with rich parameters, this minimal description leaves too much undefined.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with all parameters well-documented in the schema itself (e.g., '输入视频文件路径数组' for inputPaths, enum descriptions for codecs). The description adds no additional parameter semantics beyond implying format/resolution adaptation, which is already covered by schema fields like 'resolution', 'videoCodec', and 'audioCodec'. Baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '合并多个视频文件' (merge multiple video files) with the added feature of '智能适配' (intelligent adaptation) for different formats and resolutions. It specifies the verb (merge) and resource (video files), but doesn't explicitly distinguish it from sibling tools like 'clipVideo' or 'splitVideo' beyond mentioning format/resolution adaptation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention sibling tools like 'batchProcess' (which might handle multiple files differently) or 'clipVideo'/'splitVideo' (which modify rather than merge videos). There's no context about prerequisites, limitations, or typical use cases beyond the basic functionality stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
splitVideoC
分割视频文件,支持按时长、大小或段数分割
| Name | Required | Description | Default |
|---|---|---|---|
| inputPath | Yes | 输入视频文件路径 | |
| outputDir | Yes | 输出目录路径 | |
| splitBy | Yes | 分割方式 | |
| duration | No | 按时长分割(秒) | |
| maxSize | No | 按大小分割(MB) | |
| segmentCount | No | 分割段数 | |
| quality | No | 视频质量预设 | |
| videoCodec | No | 视频编码格式 | |
| audioCodec | No | 音频编码格式 | |
| namePattern | No | 文件命名模式,支持 {name}、{index}、{ext} 占位符 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but discloses minimal behavioral traits. It states what the tool does (splitting with three methods) but doesn't cover critical aspects: whether it's destructive to the original file, permission requirements, rate limits, error handling, or output behavior. For a tool with 10 parameters and no output schema, this leaves significant gaps in understanding how the tool behaves beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese that states the core functionality and supported methods. Every word earns its place with zero waste. It's appropriately sized for a tool with clear parameters documented elsewhere, though it could benefit from more context given the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (10 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns, error conditions, file format requirements, or how the split methods interact with encoding parameters. For a video processing tool with multiple configuration options, this leaves too much undefined for reliable agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 parameters thoroughly. The description adds no additional parameter semantics beyond implying the three split methods (duration, size, segments) which correspond to parameters splitBy, duration, maxSize, and segmentCount. This meets the baseline of 3 since the schema does the heavy lifting, but the description doesn't enhance understanding of parameter interactions or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '分割视频文件' (split video files) with specific methods '按时长、大小或段数分割' (by duration, size, or number of segments). It distinguishes from siblings like clipVideo (likely clips rather than splits) and mergeVideos, but doesn't explicitly contrast with batchProcess which might handle similar operations. The verb+resource+methods are specific, though sibling differentiation is implicit rather than explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention prerequisites (e.g., file format compatibility), when not to use it, or how it differs from siblings like clipVideo or batchProcess. The agent must infer usage from the tool name and parameters alone, which is insufficient for informed selection.
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. Dates show when Glama detected each change.
8 tool updates
- First observed
batchProcess - First observed
cancelTask - First observed
clipVideo - First observed
getSupportedFormats - First observed
getTaskStatus - First observed
getVideoInfo - First observed
mergeVideos - First observed
splitVideo
TDQS
Each tool has a clearly distinct purpose with no ambiguity: batchProcess handles bulk operations, cancelTask manages task cancellation, clipVideo performs precise trimming, getSupportedFormats lists formats, getTaskStatus checks status, getVideoInfo retrieves metadata, mergeVideos combines files, and splitVideo divides videos. The descriptions specify unique functions, making tool selection straightforward for an agent.
The naming follows a consistent verb_noun pattern throughout (e.g., clipVideo, getVideoInfo, mergeVideos), with all tools using camelCase. However, there is a minor deviation with 'batchProcess' which could be more aligned as 'processBatch' or similar, but overall the pattern is predictable and readable.
With 8 tools, the count is well-scoped for a video processing server, covering core operations like clipping, merging, splitting, and task management. Each tool earns its place by addressing specific needs in the domain, avoiding bloat while providing comprehensive functionality.
The tool set offers strong coverage for video processing, including creation (clip, merge, split), retrieval (info, formats, status), and management (cancel, batch). A minor gap exists in update operations, such as modifying video metadata or adjusting tasks, but agents can work around this with the available tools for most workflows.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
MCP server for Google Veo AI video generation
MCP server for Kling AI video generation
MCP server for Wan AI video generation
Related MCP Servers
- AlicenseBqualityFmaintenanceA Node.js server that provides advanced video and image processing capabilities through the Model Context Protocol, enabling operations like conversion, compression, editing, and effects application.101829ISC
- AlicenseBqualityDmaintenanceAn MCP server providing video processing capabilities through FFmpeg, enabling dialog-based local video search, trimming, concatenation, and playback functionalities.8145MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides video processing capabilities including format conversion, metadata extraction, and batch processing with configurable quality settings.6218MIT
- AlicenseNot gradedqualityFmaintenanceA Model Context Protocol server that enables AI assistants to perform comprehensive video and audio editing operations including trimming, effects, overlays, audio processing, and YouTube downloads.25MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pickstar-2002/video-clip-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server