What does this server do?
It provides an MCP interface to the Bilibili API, allowing MCP clients to search videos, find users, retrieve user content (videos, posts, collections), and fetch video danmaku programmatically.
@SMYB5431
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"bilibili": {
"type": "stdio",
"isActive": true,
"command": "uvx",
"args": [
"bilibili-api-mcp-server"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
An MCP (Model Context Protocol) server that wraps the Bilibili API, enabling AI assistants to search for videos and users, retrieve user content, and fetch video danmaku (bullet comments). It is intended for developers integrating Bilibili data into MCP-compatible clients.
Use uvx bilibili-api-mcp-server as the command in any MCP client’s JSON configuration. Alternatively, clone the repository, install dependencies with uv sync, and point the client to the local installation. The server exposes multiple tools for searching, user content retrieval, and danmaku fetching.
It provides an MCP interface to the Bilibili API, allowing MCP clients to search videos, find users, retrieve user content (videos, posts, collections), and fetch video danmaku programmatically.
Python with `uv` (a fast project manager). The server can be run via `uvx` from PyPI without manual installation, or cloned and run locally with `uv sync`.
Add a JSON entry under `mcpServers` with command `uvx` and args `["bilibili-api-mcp-server"]`. For local development, use `uvx` with `--directory` pointing to the cloned repository.
It accesses publicly available Bilibili data: video search results, user profiles, user dynamics (posts), video lists, collection metadata, and danmaku. No authentication or private data is required.
The README does not specify API rate limits or authentication requirements; it only mentions configurable result counts (e.g., top 15 videos by default).

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
评论