How to Use the NetEase BUFF MCP in CrewAI

Q: How do I give different NetEase BUFF tools to different agents in CrewAI?

When defining an agent, use the toolfilter argument within the MCPServerHTTP configuration. This lets you provide an explicit list of tool names from the NetEase BUFF MCP that a specific agent is allowed to use.

Q: What's the best way to track my CrewAI team's trading performance on NetEase BUFF?

Assign an 'auditor' agent to periodically call gettransactionhistory and getuserprofile. This agent can then log the results or pass a summary to another agent for reporting.

Deploy specialized AI agent teams to analyze and trade on NetEase BUFF with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NetEase BUFF MCP to CrewAI

Create your Vinkius account to connect NetEase BUFF 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 NetEase BUFF with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Agents to Watch the Market

With CrewAI, you can build a team of agents with distinct roles. Create a 'Market Analyst' agent and give it access to only the `get_market_items` and `get_price_history` tools. Its entire job is to watch for trends and find undervalued items. When it finds something, it passes the item ID and price data to a 'Strategy Agent'. This second agent uses `get_buy_orders` and `get_sell_orders` to check the current spread and liquidity, deciding if it's a real opportunity or just noise.

A Trader Agent to Execute Plays

Once your Strategy Agent greenlights a trade, it delegates the task to a 'Trader Agent'. This agent's only job is execution. You give it access to `create_buy_order` and `cancel_order`. It takes the plan and acts on it, fast. Meanwhile, an 'Auditor Agent' can run in the background. It uses `get_transaction_history` and `get_user_profile` to track the crew's overall performance and balance. This separation of duties makes your autonomous system more organized and easier to debug.

Build Your CrewAI Trading Desk

Setting this up is simple. In your CrewAI Python script, you define each agent and its role. You can pass the NetEase BUFF MCP Server URL directly to the `mcps` parameter for each agent, and use `tool_filter` to specify which tools each role can access. This prevents your Market Analyst from accidentally placing an order. It's a powerful way to enforce security and structure within your autonomous trading operation, all managed through this single MCP endpoint.

Setup guide

Set up NetEase BUFF 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 NetEase BUFF tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent NetEase BUFF 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="NetEase BUFF Analyst",
        goal="Access and analyze NetEase BUFF data via MCP.",
        backstory="Expert analyst with direct NetEase BUFF access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NetEase BUFF 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 NetEase BUFF. 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 NetEase BUFF 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 NetEase BUFF MCP in CrewAI

Yes, that's exactly what CrewAI is designed for. You can create a 'researcher' agent with read-only tools like `get_price_history` and a 'trader' agent with execution tools like `create_buy_order` from the NetEase BUFF server.

When defining an agent, use the `tool_filter` argument within the `MCPServerHTTP` configuration. This lets you provide an explicit list of tool names from the NetEase BUFF MCP that a specific agent is allowed to use.

Assign an 'auditor' agent to periodically call `get_transaction_history` and `get_user_profile`. This agent can then log the results or pass a summary to another agent for reporting.

Definitely. You can create an agent tasked with maintenance that periodically calls the `sync_inventory` tool. This ensures your crew is always working with the most up-to-date inventory data from your NetEase BUFF account.

Your CrewAI agents will access your NetEase BUFF inventory, balance, and transaction data. Each tool call is handled in a zero-trust, ephemeral environment on Vinkius. Access is controlled by a single endpoint token, ensuring your agent's session data isn't exposed or stored.

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