BiliMind

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。

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

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.

How to use

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:

Install and run the MCP server (see How to install) and ensure it is up and listening on the configured port.

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.

Code sample: basic client usage

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)

Available tools

generate_bilibili_notes

Generates structured notes from a Bilibili video by downloading audio, transcribing with Whisper, and applying an LLM to produce organized notes.

Built by

VeilStrat

AI signals for GTM teams