How to Use the Blockscout MCP in LangChain

Q: How do I add the Blockscout toolset to a LangChain agent?

Install the adapter package using pip install langchain-mcp-adapters langgraph first. Instantiated via MultiServerMCPClient, you load the tools and pass them directly to createagent to start querying EVM chains.

Q: Can LangChain trace Blockscout API latency?

Yes, every call to tools like gettransaction or getindexingstatus goes through LangSmith automatically. You get full visibility into tool inputs, outputs, and execution times.

Q: Does this Blockscout MCP Server support custom RPC methods in LangChain?

Yes, you can run custom EVM requests. Use the jsonrpc tool inside your LangChain pipeline to execute standard Ethereum JSON-RPC 2.0 payloads directly.

Q: How does LangChain handle rate limits on Blockscout?

The framework handles tool errors gracefully. If getlogs hits a rate limit, your agent catches the exception and can retry or back off based on your chain's error-handling configuration.

Chain live Blockscout blockchain data directly into your LangChain reasoning pipelines using this high-performance MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blockscout MCP to LangChain

Create your Vinkius account to connect Blockscout 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 Blockscout with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Blockscout queries with LangChain agents

Run multi-step EVM investigations by feeding the output of one Blockscout tool directly into the next. Your agent can grab a wallet's history with `get_account_transactions`, parse the contract interactions, and immediately fetch the target's code via `get_contract_source_code`. This MCP Server turns blockchain data into chainable nodes. You don't write glue code; LangChain manages the state while LangSmith traces every payload and latency spike in real time.

Real-time contract verification

Stop hardcoding ABIs or manually downloading source files. Your agent uses `get_contract_abi` to instantly pull the exact interface it needs to encode payloads. If the agent hits an unknown transaction on-chain, it pulls the block details using `get_block` and decodes logs with `get_logs` in a single execution loop. You get immediate, structured blockchain telemetry inside your active chain context.

Multi-address balance tracking

Monitor address movements by combining `get_account_balance` and `list_token_balances` across complex execution paths. Your agent tracks native coins and custom ERC-20 tokens simultaneously. When a balance shifts, the agent automatically triggers downstream LangChain tools to alert your team. You see the entire flow from raw RPC execution via `json_rpc` to the final chain output without leaving your python environment. This MCP integration keeps your runtime clean.

Setup guide

Set up Blockscout 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 Blockscout 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({
    "blockscout-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 Blockscout 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 Blockscout. 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 Blockscout 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 Blockscout MCP in LangChain

Install the adapter package using `pip install langchain-mcp-adapters langgraph` first. Instantiated via `MultiServerMCPClient`, you load the tools and pass them directly to `create_agent` to start querying EVM chains.

Yes, every call to tools like `get_transaction` or `get_indexing_status` goes through LangSmith automatically. You get full visibility into tool inputs, outputs, and execution times.

Yes, you can run custom EVM requests. Use the `json_rpc` tool inside your LangChain pipeline to execute standard Ethereum JSON-RPC 2.0 payloads directly.

The framework handles tool errors gracefully. If `get_logs` hits a rate limit, your agent catches the exception and can retry or back off based on your chain's error-handling configuration.

This server only touches public blockchain data like transaction hashes, contract addresses, and token balances. No private keys or sensitive user credentials ever pass through the Vinkius sandbox.

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