video-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_CTX | No | 超过此 token 的字幕自动分段 map-reduce | 200000 |
| LLM_MODEL | No | 模型名 | deepseek-chat |
| ASR_API_KEY | Yes | 硅基流动 key（SenseVoice 口播转写；复用 douyin-mcp 那把） | |
| LLM_API_KEY | Yes | 对应端点 key（本地 llama.cpp 可任意非空） | |
| LLM_BASE_URL | No | OpenAI 兼容端点；服务器上指 http://127.0.0.1:8080/v1 用本地 Qwen3.8 | https://api.deepseek.com/v1 |
| DOUYIN_ENGINE | No | browser（本机 Kimi WebBridge 抓签名流）/ tiktokdownloader（规划中） | browser |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| summarize_videoB | 给一个视频链接(B站/YouTube/抖音),提取字幕/口播文案并生成 Markdown 总结。 Args: url: 视频分享链接(支持 bilibili.com / b23.tv / youtube.com / youtu.be / douyin.com / v.douyin.com) lang: 输出语言,默认 zh |
| get_transcriptA | 提取视频完整字幕/口播文案。全文会写入文件(不占对话),返回摘要性提示与路径。 Args: url: 视频链接(平台同上) out_dir: 落盘目录,默认 /tmp/video-mcp |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools are related but have clear output differences: get_transcript writes the full transcript to a file, while summarize_video generates a Markdown summary. An agent could confuse them in edge cases, but the descriptions clarify their distinct purposes.
Both tool names follow the same verb_noun pattern in snake_case: get_transcript and summarize_video. This is fully consistent and predictable.
Two tools is minimal for a video-focused MCP server, covering only transcription and summarization. It is not an extreme mismatch, but the surface feels thin for the broad 'video-mcp' name.
For the apparent purpose of extracting video transcripts and generating summaries, the two core workflows are covered. However, there is no direct way to retrieve the full transcript inline, which is a minor but workable gap.