bilibili
MCP server for the bilibili API
claude mcp add --transport stdio wangshunnn-bilibili-mcp-server npx -y @wangshunnn/bilibili-mcp-server
How to use
The bilibili MCP Server exposes a set of MCP endpoints that wrap the bilibili.com API, making user info lookups, video searches, and keyword-based video searches available to MCP clients. This server is published as an npm package and can be run directly via npx or from a local clone using Node. To start using it with Claude or any MCP client, configure the mcpServers entry for bilibili in your MCP configuration file so the client can send requests to the server's endpoints (like user info by mid, or video search by bvid/keywords). The server handles requests, fetches data from bilibili, and returns structured MCP responses suitable for downstream tools.
Recommended setup (npm install/run):
- Use the npm-based quick start which runs the server via npx. This keeps the server up-to-date with the published package and is simplest for testing.
- After configuring, restart your MCP client (e.g., Claude Desktop) so it detects the new bilibili MCP option.
If you prefer to run the server from a local clone, point the node command at the built distribution’s index.js file. This is useful for development and debugging against a local workspace.
Capabilities you can rely on:
- Get user information by mid
- Search video information by bvid
- Search videos by keywords
Example endpoints (conceptual):
- GET userInfo?mid=12345
- GET videoInfo?bvid=BV1x4411x0
- GET searchVideos?query=some+keywords
Consult the MCP client’s UI to discover exact request shapes and response formats; the bilibili MCP server adapts requests into the MCP protocol as documented by the MCP ecosystem.
How to install
Prerequisites:
- Node.js (recommended LTS) installed on your machine
- Access to a terminal/command prompt
- Optional: Git if you plan to clone the repository
Install via npm (recommended):
-
Ensure you have npm installed. If you have Node.js, npm is included.
-
Install and run using npx (no local install required):
npm install -g npm@latest # (optional, ensures latest npm) npx -y @wangshunnn/bilibili-mcp-server
This will pull the bilibili-mcp-server package and run it in a temporary environment. Configure your MCP client to point at the provided bilibili MCP server entry.
If you prefer to run from a local clone:
- Clone the repository: git clone https://github.com/wangshunnn/bilibili-mcp-server.git
- Install dependencies: cd bilibili-mcp-server pnpm install # if you use pnpm; otherwise npm install
- Build (if a build step exists): pnpm build # or npm run build
- Run the server from the dist/index.js entry (adjust path to your environment): node dist/index.js
Configure your MCP client to use the bilibili server entry (as shown in the README examples) and restart the MCP client to recognize the new server.
Additional notes
Tips and common notes:
- If you run via npx, ensure the version you request (@wangshunnn/bilibili-mcp-server) is the one you want; using -y helps bypass prompts during installation.
- When running from a local clone, keep your dist/index.js path up-to-date with the latest build output.
- Some MCP clients may require a fresh restart after adding or updating the bilibili MCP server configuration.
- Environment variables (if later added) can control API keys, rate limits, or bilibili API access parameters. If you encounter rate limit issues, consider providing an API key or adjusting request pacing within the server configuration.
- For development, use the local clone option to test changes against the actual server code before publishing an update.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.