概览
What is Bilibili MCP?
Bilibili MCP is a Model Context Protocol (MCP) server for searching and retrieving Bilibili (B站) video content. It provides a simple API interface that allows AI applications to search Bilibili videos, get trending content, video details, UP主 (creator) information, and anime schedules. It is intended for developers integrating Bilibili data into MCP‑compatible AI tools.
How to use Bilibili MCP?
Bilibili MCP can be used via npx (npx bilibili-mcp-js) or by building locally from source. It supports both stdio and streamable HTTP transport (set TRANSPORT=remote and optionally PORT). Configuration is done in the MCP client’s settings (e.g., in Trae). A LangChain example and test scripts are included in the repository.
Key features of Bilibili MCP
- Search Bilibili video content with summaries
- Retrieve Bilibili hot content (comprehensive hot, must‑watch, rankings, music chart)
- Get detailed video information using BV or AV numbers
- Obtain UP主 (creator) info including followers and following counts
- Fetch anime schedule covering broadcast dates
Use cases of Bilibili MCP
- Search for Bilibili videos from an AI chatbot
- Display trending Bilibili content in a recommendation app
- Retrieve creator profiles and statistics for analysis
- Look up upcoming anime episodes within a date range
- Integrate Bilibili data into LangChain workflows
FAQ from Bilibili MCP
What are the system requirements for Bilibili MCP?
Node.js version 20.12.0 or higher is required.
How do I install and configure Bilibili MCP?
Use npx bilibili-mcp-js or build locally and run node dist/index.js. Add the command and arguments to your MCP client configuration under the key bilibili-search.
What transport modes does Bilibili MCP support?
It supports stdio (default) and streamable HTTP mode, activated by setting the environment variable TRANSPORT=remote. The port can be changed with PORT.
Is there a hosted deployment available?
Yes, a hosted deployment is available on Fronteir AI.
How can I use Bilibili MCP with LangChain?
The repository includes a LangChain example (example.ts) that uses ChatOpenAI. Configure your LLM API key and base URL in the example, then run it after building.
