bilibili-mcp MCP Server: Real-Time Hot Video Streaming

Overview: What is bilibili-mcp MCP Server?

The bilibili-mcp tool serves as an MCP (Model Context Protocol) server, designed to provide real-time access to hot video data from Bilibili's API. Built with FastMCP and leveraging Bilibili’s public APIs, this server can be registered with various AI applications through the Cursor or other MCP clients. It delivers valuable insights directly into your AI workflows, making it an indispensable resource for developers integrating AI tools.

🔧 Core Features & MCP Capabilities

The bilibili-mcp tool is equipped with several key features that align perfectly with Model Context Protocol requirements:

• GET Popular Video: Exposing a get_popular function to fetch the top-billed videos on Bilibili. This allows AI applications to seamlessly access trending content without worrying about API handling.

  import mcp
  
  # Registering the tool with FastMCP
  @mcp.tool(name="get_popular")
  def get_popular(top_k: int = 3):
      """
      Fetches popular video data from Bilibili.
  
      Arguments:
          top_k (int): The number of top videos to retrieve. Maximum limit is 10.
      
      Returns:
          List[dict]: A list containing dictionary objects representing the selected videos. Each object includes attributes like 'title', 'view', and 'like'.
      """
      # Fetch data from Bilibili API
      popular_videos = fetch_bilibili_api()
  
      return popular_videos[:top_k]
  

• MCP Server Registration: The bilibili-mcp automatically registers as a standard MCP tool, ready to be discovered by any compatible MCP client.

⚙️ MCP Architecture & Protocol Implementation

The server leverages the httpx library for asynchronous requests and integrates with FastMCP to ensure seamless communication with AI applications. This setup is designed to handle real-time data fetching efficiently while maintaining compatibility across different environments.

Mermaid Diagram: MCP Protocol Flow

graph TD
    A[AI Application] -->|MCP Client| B[MCP Protocol]
    B --> C[MCP Server]
    C --> D[Data Source/Tool]
    style A fill:#e1f5fe
    style C fill:#f3e5f5
    style D fill:#e8f5e8

Mermaid Diagram: Data Architecture

graph TD;
  A[API Request] --> B[MCP Server];
  B --> C[Database/Cache];
  C --> D[Data Source];
  D --> E[Video Data Collection];
  E --> F[API Response];
  F --> G[MCP Client];

🚀 Getting Started with Installation

To set up and run the bilibili-mcp server, follow these steps:

1. Ensure Python version ≥ 3.12 is installed.

2. Install the required dependencies:

   pip install httpx "mcp[cli]>=1.6.0"
   

3. Define your project structure with a main code file named bilibili_mcp.py along with necessary configuration files.

4. Run the server using the following command:

   uv tool run bilibili-mcp
   

5. Alternatively, you can use a JSON configuration to start the tool automatically when running via an MCP client like Cursor:

   "bilibili-mcp": {
     "command": "uv",
     "args": [
       "tool",
       "run",
       "bilibili-mcp"
     ]
   }
   

💡 Key Use Cases in AI Workflows

The bilibili-mcp server is ideal for integrating real-time video information into various AI workflows, such as:

• Real-Time Trending Videos: Display the latest trending videos on a dashboard or within an application.
• Content Moderation: Utilize AI models to moderate and filter videos based on popularity and relevance.

🔌 Integration with MCP Clients

The server is compatible with a range of MCP clients, including but not limited to:

• Claude Desktop: Full support for fetching data through the get_popular tool.
• Continue: Supports all functionalities provided by FastMCP tools.
• Cursor: Limited compatibility as it only supports specific tools and APIs.

Mermaid Table: MCP Client Compatibility Matrix

table
| MCP Client | Resources | Tools | Prompts |
|------------|-----------|-------|---------|
| Claude Desktop | ✅ | ✅ | ✅ | Full Support |
| Continue | ✅ | ✅ | ✅ | Full Support |
| Cursor | ❌ | ✅ | ❌ | Tools Only |

📊 Performance & Compatibility Matrix

• Performance: The server is optimized for low-latency data retrieval, ensuring minimal latency between request and response.
• Compatibility: The protocol adheres to MCP standards, supporting multiple clients with varying levels of integration.

🛠️ Advanced Configuration & Security

For advanced users, here are some configuration options:

{
  "mcpServers": {
    "[server-name]": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-[name]"],
      "env": {
        "API_KEY": "your-api-key"
      }
    }
  }
}

Ensure to secure your environment variables and API keys for production environments.

❓ Frequently Asked Questions (FAQ)

1. Q: How can I integrate the bilibili-mcp server with my AI application?

   • A: Use the get_popular tool provided by FastMCP to access Bilibili hot video data. Register your tool and start fetching real-time video information.

2. Q: Is there any limitation on the use of this server?

   • A: It is intended for learning and research purposes only. Avoid making excessive API calls to respect resource limitations.

3. Q: Can I change the User-Agent string?

   • A: Yes, you can modify the User-Agent in your environment variables or configuration files as needed.

4. Q: What kind of data is returned by the get_popular method?

   • A: The response includes video titles, links, descriptions, view counts, and likes, formatted as a list of dictionaries.

5. Q: Are there any performance guarantees provided by this setup?

   • A: While efforts are made to optimize latency, performance may vary based on network conditions and resource availability.

👨‍💻 Development & Contribution Guidelines

Contributions are welcome! Here’s how you can help:

1. Fork the repository.
2. Make changes or improvements.
3. Submit a pull request.

Please follow standard Pull Request guidelines for detailed instructions.

🌐 MCP Ecosystem & Resources

• Official Documentation: Model Context Protocol Documentation
• FastMCP GitHub Page: FastMCP GitHub Repository

Conclusion

The bilibili-mcp server stands as a robust solution for AI applications looking to integrate real-time video data from Bilibili. By supporting MCP standards and delivering efficient, scalable access to trending content, this tool can significantly enhance the capabilities of your AI workflows.

By understanding how bilibili-mcp fits into the broader MCP ecosystem, developers can leverage its functionalities with confidence, ensuring seamless integration across various platforms and applications.