home / mcp / bilimind mcp server
基于 MCP的B站视频智能助手，提供视频内容转录、智能问答和笔记生成服务。
Configuration
View docs{
"mcpServers": {
"jiaohuix-bilimind-mcp": {
"command": "python",
"args": [
"demo/bilimind_mcp.py"
],
"env": {
"API_BASE": "YOUR_API_BASE",
"MCP_PORT": "8001",
"OPENAI_API_KEY": "YOUR_API_KEY",
"DEFAULT_MODEL_DIR": "./models",
"DEFAULT_OUTPUT_DIR": "./downloads",
"WHISPER_MODEL_SIZE": "tiny"
}
}
}
}You are running an MCP server that converts Bilibili videos into structured notes. It downloads audio, transcribes it with Whisper, and uses a language model to produce organized notes that you can access through a simple MCP interface. This makes it easy to turn video content into searchable, consumable notes for study, review, or reference.
You connect a client to the MCP server and request note generation for a Bilibili video URL. The server exposes a standard MCP interface you can call from your application. You provide the video URL, and the server handles downloading audio, transcribing, and turning the transcript into structured notes.
Typical workflow you can follow:
Create a client in your application and connect to the MCP server. Use the client to request notes for a Bilibili video URL. The server returns structured notes that you can render in your UI or save for later.
If you prefer an example snippet, the client usage typically involves creating a client instance with your MCP server name and then calling a function designed to generate notes from a Bilibili URL. The server handles all the heavy lifting and returns the resulting notes.
from mcp.client import Client
# Connect to the MCP server by its logical name
client = Client("bili_note_generator")
# Request notes for a Bilibili video URL
video_url = "https://www.bilibili.com/video/BVxxxxxx"
note_result = await client.generate_bilibili_notes(video_url)
print(note_result)Generates structured notes from a Bilibili video by downloading audio, transcribing with Whisper, and applying an LLM to produce organized notes.