How to Use the Zerion (DeFi Portfolio) MCP in LangChain

Q: What kind of data does Zerion (DeFi Portfolio) help with in LangChain?

It handles everything from token metadata (getfungible) to specific NFT holdings (getnft) and full transaction history. It’s a massive amount of financial state information.

Build complex DeFi logic with LangChain and Zerion (DeFi Portfolio)

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zerion (DeFi Portfolio) MCP to LangChain

Create your Vinkius account to connect Zerion (DeFi Portfolio) 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 Zerion (DeFi Portfolio) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Reasoning for LangChain

The `get_wallet_portfolio` tool provides the total value of a wallet. You can then chain this output into `get_wallet_pnl` to figure out realized versus unrealized gains. This allows your agent to build complex, multi-step reasoning pipelines that determine if a trade is profitable based on multiple data points. LangChain excels here because every tool call acts like a link in a chain. The output of checking total assets feeds directly into calculating PnL or determining the most active chains via `list_chains`. This gives you full observability into how your agent arrives at its final decision.

Tracking DeFi Assets with MCP Server

Need to track holdings across multiple wallets? Use `get_wallet_set_portfolio` to get an aggregated view of assets. This single call gives you the total value and distribution for a set of addresses, which is critical when managing complex institutional accounts. Don't just check one wallet; aggregate them all at once. Your agent can compare multiple portfolio snapshots using `get_wallet_set_positions` against real-time gas estimates from `list_gas_prices` before recommending a cross-chain swap quote via `get_swap_quotes`.

Analyzing Transaction Chains for LangChain

To build an accurate historical view, start with the `get_wallet_transactions` tool. This gives you a human-readable history of activities across a specific address. Your agent can then read those transactions and use that data to inform subsequent calls. For example, if a transaction shows movement into a new NFT collection, your next step is automatically calling `get_nft` to grab the metadata for that asset. It's all one continuous flow.

Setup guide

Set up Zerion (DeFi Portfolio) 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 Zerion (DeFi Portfolio) 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({
    "zerion-defi-portfolio-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 Zerion (DeFi Portfolio) 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 Zerion. 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 Zerion (DeFi Portfolio) 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 Zerion (DeFi Portfolio) MCP in LangChain

LangChain treats the MCP Server as a tool, not just data. You feed it the tools list, and your agent figures out the best order to call them. This allows you to build logic that goes far beyond simple lookups.

You'll write multi-step pipelines. You might start by listing supported blockchains with `list_chains`, then check the gas prices for those chains, and finally run a cross-chain quote to see if it’s worth doing.

Absolutely. The agent decides which tool to call and when, making it perfect for autonomous decision-making. It's built for advanced orchestration.

It handles everything from token metadata (`get_fungible`) to specific NFT holdings (`get_nft`) and full transaction history. It’s a massive amount of financial state information.

The server touches wallet positions and transaction history. You control the inputs, ensuring your agent only uses the specific set of addresses or time frames you authorize.

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