How to Use the Douyu MCP in AutoGen

Q: How do I add the Douyu tools to an AutoGen agent via MCP?

Install the extension with pip install -U "autogen-extmcp". Use StreamableHttpServerParams to point to your Vinkius endpoint, and the McpToolAdapter will automatically register the tools for your AssistantAgent.

Q: How is my Douyu chat message data secured during agent execution?

Any message content sent via sendmessage is processed in an ephemeral V8 sandbox container. Vinkius does not retain the payload or log the text of your chat messages after they are sent to the Douyu API.

Let AutoGen agents debate and coordinate live Douyu chat moderation and performance tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Douyu MCP to AutoGen

Create your Vinkius account to connect Douyu to AutoGen 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 Douyu with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate AutoGen agents with this MCP Server

It's easy to build AutoGen teams that collaborate to find high-performing broadcasts. A scout agent can use `search_streamers` and `get_live_rooms` to gather candidate lists, while an analyst agent evaluates their metrics. By integrating this MCP Server, your agents can make coordinated decisions. Once they agree on a target, they use `get_room_detail` to pull deep-dive metrics and confirm if the streamer meets your performance criteria.

Automated chat interaction and moderation loops

Set up AutoGen agents to manage live interactions on Douyu. One agent can monitor the chat environment using `get_danmu_config` to check connection parameters, while a communication agent uses `send_message` to post updates or moderate discussions. The agents negotiate the tone and timing of messages before sending them. This prevents a single agent from spamming the stream and ensures all posted content aligns with your pre-defined communication guidelines.

Collaborative donor and user analysis

Analyze monetization and audience demographics using specialized agents. A finance agent runs `get_top_donators` to track high-value tippers, while a profiling agent uses `get_user_stats` to inspect individual user profiles and estimate retention. The agents debate which contributors have the highest impact on a stream's ecosystem. They can also coordinate to use `follow_streamer` on creators who show consistent growth and high viewer loyalty.

Setup guide

Set up Douyu MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Douyu tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Douyu_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Douyu data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Douyu_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Douyu data")
    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 Douyu. 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 Douyu 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 Douyu MCP in AutoGen

Install the extension with pip install -U "autogen-ext[mcp]". Use StreamableHttpServerParams to point to your Vinkius endpoint, and the McpToolAdapter will automatically register the tools for your AssistantAgent.

Yes, you can set up a conversation where one agent analyzes streamer stats using get_room_detail and another checks their donor leaderboard via get_top_donators. They will debate the streamer's ROI before executing follow_streamer.

You should configure your agents' system prompts to limit how often they call tools like get_gift_list. The McpToolAdapter handles the execution, but your agents need to coordinate to avoid redundant requests.

Yes, the server is fully compatible with both transport layers. When running on Vinkius, you will typically use the Streamable HTTP transport to connect your AutoGen agents.

Any message content sent via send_message is processed in an ephemeral V8 sandbox container. Vinkius does not retain the payload or log the text of your chat messages after they are sent to the Douyu API.

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