How to Use the DeBank (DeFi Wallet Tracker) MCP in AutoGen

Q: Can I use the DeBank (DeFi Wallet Tracker) MCP Server with AutoGen to analyze whale wallets?

Yes, absolutely. Tools like getuserhistorylist and getusertokenlist take a public wallet address as an argument. You can build an AutoGen team to monitor any wallet you want, track their trades, and analyze their strategy.

Q: What's a good multi-agent setup for protocol analysis using DeBank (DeFi Wallet Tracker) and AutoGen?

Here’s a solid approach. Have one agent use getprotocol to pull the basics. A second, more skeptical agent can use gettokentopholders on the protocol's token to check for whale concentration. They can then debate the protocol's real health and decentralization.

Let your AutoGen agents debate DeFi strategies using real-time wallet, protocol, and transaction data from DeBank.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeBank (DeFi Wallet Tracker) MCP to AutoGen

Create your Vinkius account to connect DeBank (DeFi Wallet Tracker) 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 DeBank (DeFi Wallet Tracker) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Wallet-Aware Agent Teams

This server gives your agents direct access to any wallet's on-chain life. Use tools like `get_user_total_balance`, `get_user_token_list`, and `get_user_complex_protocol_list` to pull a complete financial picture. One agent can fetch the raw data for a target wallet. Then, a second agent can analyze it for risk. Is the portfolio over-exposed to one token? Are they in sketchy protocols? AutoGen lets them argue about it, presenting you with a consensus on the wallet's actual risk profile, not just a data dump.

Your AutoGen MCP Server for On-Chain Debate

Give your agents the tools to find actual alpha. One agent can monitor gas prices with `get_gas_market` while another scans for opportunities with `get_pool` and `get_protocol`. You're not just getting data points; you're setting up a system to interpret them. The real power comes when they disagree. The gas-watching agent might argue a transaction is too expensive right now. The yield-hunting agent sees a fleeting opportunity. With AutoGen, they can debate the trade-offs and recommend a specific action, complete with their reasoning.

Simulate and Explain Transactions

Stop guessing what a transaction will do. The `pre_exec_tx` tool simulates a transaction against the live chain state, showing you exactly what will happen to balances before you sign anything. Another key tool, `explain_tx`, translates cryptic transaction data into plain English. This is perfect for a security-focused agent team. One agent simulates the transaction, another checks the wallet's existing permissions with `get_user_token_authorized_list`. If the transaction tries to interact with a risky contract, your agents can flag it before you lose a dime.

Setup guide

Set up DeBank (DeFi Wallet Tracker) 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 DeBank (DeFi Wallet Tracker) 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="DeBank (DeFi Wallet Tracker)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DeBank (DeFi Wallet Tracker) 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="DeBank (DeFi Wallet Tracker)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DeBank (DeFi Wallet Tracker) 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 DeBank. 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 DeBank (DeFi Wallet Tracker) 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 DeBank (DeFi Wallet Tracker) MCP in AutoGen

It’s straightforward. After the pip install, you just point to the MCP server endpoint Vinkius gives you. The McpToolAdapter handles the tool definitions, so you pass them right to your AssistantAgent and start the conversation.

Yes, absolutely. Tools like `get_user_history_list` and `get_user_token_list` take a public wallet address as an argument. You can build an AutoGen team to monitor any wallet you want, track their trades, and analyze their strategy.

Here’s a solid approach. Have one agent use `get_protocol` to pull the basics. A second, more skeptical agent can use `get_token_top_holders` on the protocol's token to check for whale concentration. They can then debate the protocol's real health and decentralization.

The list is always changing. Instead of checking a static list here, just have your agent call the `list_chains` tool. That gives you the definitive, up-to-the-minute list of supported chains directly from the source.

This server only ever touches public blockchain data associated with the wallet addresses you provide. It doesn't ask for, see, or store your private keys. Every request runs in a dedicated, ephemeral sandbox that's torn down after, and Vinkius handles the secure connection.

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