How to Use the IoTeX (IoTeX Block Explorer API) MCP in LangChain

Q: How do I feed token holder data from IoTeX into a LangChain vector store?

You pull the data using gettokenholders and pass the raw JSON to your LangChain document loaders. From there, your pipeline splits and embeds the holder addresses and balances directly into your vector database for semantic querying.

Q: Can a LangChain agent verify transaction payloads on IoTeX (IoTeX Block Explorer API) automatically?

Yes, the agent uses getaction to inspect specific hashes and confirm execution success. You can configure a chain that checks a transaction hash, verifies the gas used, and routes the workflow based on whether the transaction succeeded or failed.

Run multi-step reasoning pipelines that query live IoTeX blockchain data directly inside your LangChain chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IoTeX (IoTeX Block Explorer API) MCP to LangChain

Create your Vinkius account to connect IoTeX (IoTeX Block Explorer API) 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 IoTeX (IoTeX Block Explorer API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain IoTeX account audits with LangChain agents

The `get_account` and `get_account_actions` tools let your agent fetch live balances and transaction history in a single execution step. Your agent takes the output from a balance check, evaluates if it meets a threshold, and immediately triggers the next action in your sequence. This setup eliminates manual state management so you don't have to write custom polling loops. By feeding raw blockchain data directly into your LangChain runnables using this MCP Server setup, you build self-correcting pipelines that verify wallet activity before executing dependent smart contract tasks.

Track real-time transactions using this MCP Server

The `get_recent_actions` and `get_action` tools pull the latest transaction logs straight into your active prompt context via the MCP protocol. Your agent parses these payloads to trace execution paths, catch failed transactions, and extract event logs without waiting for manual indexer updates. You get raw transaction data structured for immediate decision-making. The agent inspects specific action hashes on the fly to confirm gas usage and execution status, feeding those metrics back into your main LangChain execution loop.

Deep token holder analysis

The `get_token` and `get_token_holders` tools expose contract metadata and ownership distribution directly to your reasoning models. Your agent queries these endpoints to identify top holders and verify token supply metrics during automated market analysis. By connecting these tools to your chains, you bypass complex web3 library setups. The agent handles the raw JSON responses, filtering out noise and presenting clean token distributions to your analytical pipelines.

Setup guide

Set up IoTeX (IoTeX Block Explorer API) 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 IoTeX (IoTeX Block Explorer API) 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({
    "iotex-iotex-block-explorer-api-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 IoTeX (IoTeX Block Explorer API) 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 IoTeX. 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 IoTeX (IoTeX Block Explorer API) 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 IoTeX (IoTeX Block Explorer API) MCP in LangChain

Yes, you can track blocks dynamically. Your LangChain agent uses `get_block_by_height` and `get_block_by_hash` to retrieve block data as soon as it is minted. This lets you build chains that react to new ledger states without polling lag.

You pull the data using `get_token_holders` and pass the raw JSON to your LangChain document loaders. From there, your pipeline splits and embeds the holder addresses and balances directly into your vector database for semantic querying.

You should implement a standard rate-limiting runnable or a queue system in your LangChain graph. The server queries the public explorer API directly, so wrapping your tool calls in a retry backoff loop prevents HTTP 429 errors during heavy runs.

Yes, the agent uses `get_action` to inspect specific hashes and confirm execution success. You can configure a chain that checks a transaction hash, verifies the gas used, and routes the workflow based on whether the transaction succeeded or failed.

This server only handles public ledger data like account addresses, transaction hashes, and token balances. No private keys or sensitive credentials are ever processed or exposed. Vinkius runs the server in an isolated sandbox, ensuring your query parameters remain private and secure during execution.

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