Allows downloading, transcribing, and analyzing Bilibili videos, including searching by keyword or natural language intent.
Click on "Deploy 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., "@vid-agent-mcp 转录一下这个视频 BV1pzjy6GEkC"
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.
MCP server for video understanding — transcribe Bilibili videos, search, and analyze local files through natural conversation with Claude.
Chat with Claude and ask it to watch a video for you. Send a Bilibili link, get back a structured summary with key points, visual moments, and a "worth watching" verdict — all through MCP tools.
You: "转录一下这个视频 BV1pzjy6GEkC"
Claude: *calls transcribe tool*
→ Downloads video via BBDown
→ Transcribes audio with faster-whisper
→ Identifies key visual moments via VLM
→ Returns structured summary
You: "最近有什么AI Agent新视频？"
Claude: *calls search_by_intent tool*
→ Expands intent into multiple search queries
→ Searches Bilibili concurrently
→ Merges & ranks results by popularityRelated MCP server: Bilibili API MCP Server
Tool | Description |
| Download + analyze a Bilibili video |
| Analyze a local video file |
| Search Bilibili by keyword |
| AI-powered search with natural language |
| Read a previously saved result |
Python 3.11+
ffmpeg (install via conda install ffmpeg or system package manager)
BBDown (for Bilibili downloads) — install from here or use an existing install
A MiMo API key (or any OpenAI-compatible VLM API)
# 1. Clone
git clone https://github.com/ikerrrrrrrrrrr/bili-vid-agent
cd bili-vid-agent
# Or install the MCP server directly
pip install vid-agent-mcp
# 2. Configure
cp .env.example .env
# Edit .env with your API key
# 3. Run
vid-agent-mcpAdd to your claude_desktop_config.json:
{
"mcpServers": {
"vid-agent": {
"command": "vid-agent-mcp",
"env": {
"VLM_API_KEY": "your-key-here"
}
}
}
}Or point to a local install:
{
"mcpServers": {
"vid-agent": {
"command": "conda",
"args": ["run", "-n", "vid_agent", "vid-agent-mcp"]
}
}
}All config via .env file or environment variables:
Variable | Default | Description |
| — | MiMo API key (required) |
|
| API base URL |
|
| Model for visual analysis |
|
| Model for summary generation |
|
| Path to BBDown binary |
|
| Whisper model size |
|
| Download/transcription cache |
|
| Working directory |
Apache 2.0
This server cannot be deployed
Bilibili public video, article, dynamic, creator, comments, reactions, and transcript tools.
Video analysis AI: transcripts, summaries, visual scenes/shots, clips, answers in natural language.
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
