How to Use the Douyu MCP in CrewAI

Q: What is the best way to track virtual gifts in a stream?

Use getgiftlist to fetch the active catalog of virtual items for any given room. Your analysis agent can match this list against live chat activity to calculate real-time transaction values. This reveals which moments in a broadcast generate the highest monetization.

Run a crew of specialized CrewAI agents to track live rooms, analyze chat sentiment, and manage viewer metrics on Douyu.

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 CrewAI

Create your Vinkius account to connect Douyu to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate esports tracking with CrewAI agents

`get_live_rooms` identifies active broadcasts within specific categories so your research agent can build a target list. Once the active rooms are identified, your analysis agent calls `get_room_detail` to extract real-time viewer numbers and stream titles. This setup lets you monitor the entire directory without human supervision. Your agents coordinate these tasks in sequence. While one agent filters the live directory, another evaluates individual stream health. You get clean, structured data delivered directly to your database.

Connect a dedicated MCP Server to monitor live chat

`get_danmu_config` retrieves the exact WebSocket connection parameters required to hook into active stream chats. A dedicated moderator agent can then watch the live comment flow while a second agent uses `send_message` to post alerts or interact with viewers. This establishes a direct feedback loop between your AI team and the live audience. This MCP Server runs inside a secure V8 sandbox on Vinkius. Your agents execute chat operations without risking local environment exposure or leaking system credentials.

Map viewer retention and donation leaders

`get_top_donators` extracts the weekly and monthly leaderboard data to map high-value user engagement. Your financial agent combines this with `get_user_stats` to profile top spenders and track audience retention patterns over time. You don't guess which creators drive revenue; you see the hard numbers. Your crew runs this analysis on a schedule. One agent pulls the raw leaderboards, a second agent runs the user lookup, and a third compiles the final performance report.

Setup guide

Set up Douyu MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Douyu tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Douyu Analyst",
    goal="Access and analyze Douyu data via MCP.",
    backstory="Expert analyst with direct Douyu access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Douyu transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Douyu Analyst",
        goal="Access and analyze Douyu data via MCP.",
        backstory="Expert analyst with direct Douyu access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Douyu transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the Vinkius endpoint URL directly into your agent definition using the mcps parameter. Run pip install crewai "crewai[tools]" first to ensure your environment supports the protocol. Vinkius handles the underlying connection, so your agents get immediate access to all ten live-streaming tools.

Yes, your agent can post directly to live streams using send_message. You must provide a valid OAuth token during the Vinkius setup. Once configured, your specialized communication agent can execute this action based on triggers from other agents.

You should configure your sequential tasks with deliberate backoff delays. While the MCP tools fetch data instantly, making rapid calls to get_room_detail can trigger platform limits. Designing your crew with a coordinator agent that manages polling intervals keeps your integration running smoothly.

Use get_gift_list to fetch the active catalog of virtual items for any given room. Your analysis agent can match this list against live chat activity to calculate real-time transaction values. This reveals which moments in a broadcast generate the highest monetization.

Your credentials and retrieved user profile data are processed within isolated V8 sandboxes that spin down immediately after execution. Vinkius operates on a zero-trust model, meaning your authentication tokens are never stored or exposed to external networks. Every request is ephemeral, keeping your operational data entirely private.

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