How to Use the Etherscan MCP in LangChain

Q: How do I configure the Etherscan MCP Server inside my LangChain project?

Install langchain-mcp-adapters and langgraph via pip, then initialize the MultiServerMCPClient with the Vinkius transport URL to expose Etherscan tools. Call client.gettools() to pass the Ethereum endpoints directly to your LangChain agent constructor.

Q: Can I use Etherscan to fetch ERC-721 transfers using LangChain?

Yes, the gettokennfttx Etherscan tool retrieves standard NFT transfer histories directly into your LangChain agent's context. Your LangChain chain can immediately parse these Etherscan transfer events to track provenance or flag suspicious high-value trades.

Feed live Ethereum ledger data from Etherscan into your LangChain chains to automate smart contract audits and trace wallet balances in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Etherscan MCP to LangChain

Create your Vinkius account to connect Etherscan 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 Etherscan with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Etherscan metrics to feed LangChain agents

The Etherscan MCP Server exposes `get_balance` and `get_gas_oracle` to supply raw Ethereum blockchain state directly to your custom LangChain execution chains. Your LangChain agent reads the current Ethereum gas price via the Etherscan `get_gas_oracle` tool to decide the next link in your sequential chain execution. By linking these Etherscan tool calls, the balance output from `get_balance` feeds directly into the parameter inputs of your next LangChain step. This prevents failed Ethereum transactions due to insufficient gas during automated LangChain execution loops.

Trace smart contract audits with LangSmith

The `get_source_code` and `get_abi` Etherscan tools pull verified Ethereum contract data directly into your LangChain multi-step auditing pipelines. Your LangChain agent pulls the Solidity source code from Etherscan, runs a structural analysis, and extracts the ABI to map out potential attack vectors. Every single Etherscan tool execution is tracked in LangSmith to show you exactly how your LangChain LLM parsed the Solidity code. You see the precise latency, token cost, and raw string output of the Etherscan contract retrieval step without guessing where your LangChain pipeline failed.

Run multi-step transaction tracing

The `get_tx_list` and `get_token_tx` Etherscan tools let your LangChain ReAct agent reconstruct complex token flow history across thousands of blocks. The LangChain agent loops through historical Etherscan transfers, identifies counterparty addresses, and maps out the flow of funds step-by-step. Because LangChain supports MCP multi-server aggregation, you can combine this Etherscan blockchain data with external database tools in the same runtime. This allows your LangChain agent to cross-reference Etherscan wallet addresses with off-chain identity databases instantly.

Setup guide

Set up Etherscan 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 Etherscan 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({
    "etherscan-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 Etherscan 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 Etherscan. 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 Etherscan 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 Etherscan MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip, then initialize the `MultiServerMCPClient` with the Vinkius transport URL to expose Etherscan tools. Call `client.get_tools()` to pass the Ethereum endpoints directly to your LangChain agent constructor.

Yes, the LangChain ReAct agent loop evaluates the chain step-by-step, choosing to call `get_block_number` first and then fetching specific Etherscan logs with `get_logs` based on the block height. You get structured outcomes because each Etherscan tool output directly informs the next LangChain agent decision.

You must manage rate limits at the adapter level or configure retries within your LangGraph runtimes when making heavy Etherscan calls like `get_balance_multi`. The Etherscan server passes raw API errors back to LangChain, allowing your error-handling steps to pause and retry gracefully.

Yes, the `get_token_nft_tx` Etherscan tool retrieves standard NFT transfer histories directly into your LangChain agent's context. Your LangChain chain can immediately parse these Etherscan transfer events to track provenance or flag suspicious high-value trades.

No, the LangChain adapter transmits queries to Vinkius, which processes public Ethereum addresses and contract ABIs in ephemeral V8 sandboxes. Your sensitive LangChain session variables and Etherscan API keys are completely isolated from external logs.

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