About Bilibili MCP
Bilibili MCP is an MCP server for searching Bilibili video content from AI applications. It offers search, trending lists, video and uploader details, and anime schedules, and includes a LangChain example and test scripts.
Key features
- 01Search Bilibili video listings
- 02Fetch trending lists and rankings
- 03Get video details by BV or AV number
- 04Retrieve uploader profile and follower data
- 05Query anime broadcast schedules by date range
Use cases
- 01Search Bilibili videos from an AI application
- 02Call Bilibili data from a LangChain agent
- 03Check anime broadcast schedules
MCP support
This is an MCP server that exposes Bilibili search, trending, video detail, uploader, and anime schedule capabilities to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBilibili MCP
简介
这是一个基于 Model Context Protocol (MCP) 的 B站视频搜索服务器。该服务器提供了简单的 API 接口,允许用户搜索 B站 的视频内容。提供LangChain调用示例、测试脚本。
鸣谢
- LangChain 示例代码参考自 mcp-langchain-ts-client
功能特点
- 搜索B站视频内容简介列表
- 获取B站热门内容(综合热门、入站必刷、排行榜、全站音乐榜)
- 获取B站视频详情信息(支持BV号或AV号)
- 获取UP主信息(基本信息、粉丝数、关注数等)
- 番剧时间表(时间范围内的番剧播出信息)
系统要求
- Node.js >= 20.12.0
AI工具使用配置
以Trae为例

npm package
感谢HQHC发布的npm包
{
"mcpServers": {
"bilibili-search": {
"command": "npx",
"args": ["bilibili-mcp-js"],
"description": "B站视频搜索 MCP 服务,可以在AI应用中搜索B站视频内容。"
}
}
}
本地编译使用
需要编译之后才可以使用. 先npm run build然后这里改成你build之后的dist文件夹路径,"args": ["d:\your-path\bilibili-mcp-js\dist\index.js"]
{
"mcpServers": {
"bilibili-search": {
"command": "node",
"args": ["d:\\your-path\\bilibili-mcp-js\\dist\\index.js"],
"description": "B站视频搜索 MCP 服务,可以在AI应用中搜索B站视频内容。"
}
}
}
快速开始
如果要运行langchain例子,请先配置llm模型,修改.\example.ts文件。
const llm = new ChatOpenAI({
modelName: "gpt-4o-mini",
temperature: 0,
openAIApiKey: "your_api_key", // 替换成你模型的密钥
configuration: {
baseURL: "https://www.api.com/v1", // 替换成你模型的API地址
},
});
bun:
# 安装依赖
bun i
# stdio 模式
bun index.ts
# streamable http 模式
TRANSPORT=remote bun index.ts
TRANSPORT=remote PORT=8888 bun index.ts
# 测试脚本
bun test.js
# MCP Inspector
bun run inspector
# 运行langchain例子
bun build:bun
bun example.ts
npm:
# 安装依赖
npm i
# stdio 模式
npm run start
# streamable http 模式
TRANSPORT=remote npm run start
TRANSPORT=remote PORT=8888 npm run start
# 测试脚本
npm run test
# MCP Inspector
npm run inspector
# 运行langchain例子
npm run build
node dist/example.js
截图

Hosted deployment
A hosted deployment is available on Fronteir AI.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.