How to Use the Bilibili Live MCP in LangChain

Q: How do I hook Bilibili Live tools into a LangChain agent?

Install langchain-mcp-adapters and use MultiServerMCPClient to connect to the server URL. You then call client.gettools() and pass them directly to your agent constructor to start processing stream data.

Q: Can LangChain track the latency of Bilibili Live API calls?

Yes, every time your agent calls getgifthistory or getroominfo, LangSmith traces the execution. You see the exact millisecond latency and token usage for each Bilibili interaction.

Q: How does LangChain handle connection state with Bilibili Live?

The tools are stateless, but you can use client.session() to maintain persistent context across multiple runs. This lets your agent remember previous websocket details obtained from getdanmuconfig during a long broadcast.

Q: Can I send chat messages back to the stream?

Yes. Your agent uses the senddanmu tool to post replies directly to the live feed using your developer account credentials.

Q: Is my Bilibili Live developer credential safe?

Absolutely. All credentials, broadcaster details from getstreamerinfo, and websocket configs remain inside the Vinkius V8 sandboxed environment. Your raw stream authentication tokens never touch the public internet or external LLM logging systems.

Build multi-step LangChain pipelines that monitor Bilibili Live rooms, parse super chats, and automate broadcaster responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bilibili Live MCP to LangChain

Create your Vinkius account to connect Bilibili Live to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bilibili Live with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build reactive Bilibili Live room management chains

This MCP Server lets your LangChain agent hook directly into live stream playback configurations via `get_room_play_info`. By feeding these Bilibili live status updates into a LangChain ReAct agent, you construct feedback loops that monitor stream health and update the broadcast details dynamically.

Automate Bilibili Live viewer tier rewards inside LangChain

This MCP Server exposes Bilibili viewer loyalty data directly to your LangChain agentic workflows. Your LangChain agent runs `get_fans_medal_info` to verify subscriber ranks and routes high-tier fans through custom logic paths instantly.

Real-time chat analysis with LangChain adapters

This MCP Server connects your LangChain LLM pipelines to live Bilibili chat feeds. Your LangChain agent initiates WebSocket connections via `get_danmu_config` to stream raw bullet chat data directly into your LangChain memory buffers.

Setup guide

Set up Bilibili Live MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Bilibili Live tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "bilibili-live-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Bilibili Live transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bilibili Live. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bilibili Live now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bilibili Live MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` to connect to the server URL. You then call `client.get_tools()` and pass them directly to your agent constructor to start processing stream data.

Yes, every time your agent calls `get_gift_history` or `get_room_info`, LangSmith traces the execution. You see the exact millisecond latency and token usage for each Bilibili interaction.

The tools are stateless, but you can use `client.session()` to maintain persistent context across multiple runs. This lets your agent remember previous websocket details obtained from `get_danmu_config` during a long broadcast.

Yes. Your agent uses the `send_danmu` tool to post replies directly to the live feed using your developer account credentials.

Absolutely. All credentials, broadcaster details from `get_streamer_info`, and websocket configs remain inside the Vinkius V8 sandboxed environment. Your raw stream authentication tokens never touch the public internet or external LLM logging systems.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript