How to Use the Nodereal MCP in LangChain

Q: How do I connect the Nodereal MCP Server to LangChain?

Install langchain-mcp-adapters and initialize a MultiServerMCPClient. Pass the HTTP transport URL for the server. Then call client.gettools() and feed the list into your agent constructor.

Q: Are Nodereal's enhanced APIs available through MCP?

They are. Tools like nrgetnftinventory and nrgetassettransfers are fully registered. Your agent calls them exactly like standard RPC endpoints.

Build multi-step blockchain query pipelines with the Nodereal MCP server in LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nodereal MCP to LangChain

Create your Vinkius account to connect Nodereal 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 Nodereal with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain EVM and Aptos Data in LangChain

`eth_get_balance` and `aptos_get_account_resources` form the foundation of this MCP Server, letting your ReAct agents pull raw state directly from the chain. You don't have to write custom RPC wrappers. The agent decides when to check a balance and when to pull the full resource tree based on the user's prompt. Because LangChain treats every tool as a composable link, you can pass the output of `eth_get_block_by_number` straight into `nr_get_transaction_receipts_by_block_number`. The agent handles the data transformation. You just watch the execution graph in LangSmith to see exactly how much latency the node calls introduce.

Simulate Transactions Before Execution

`aptos_simulate_transaction` lets your agent dry-run complex Move calls before committing anything to the network. This prevents failed transactions and wasted gas fees. Your agent constructs the payload, runs the simulation, and parses the outcome. If the simulation fails, the agent can adjust the gas parameters using `eth_estimate_gas` for EVM equivalents or rewrite the transaction arguments entirely. You get a self-correcting pipeline that validates state changes against live chain data instead of guessing.

Query Enhanced NodeReal Indexes

`nr_get_nft_holders` and `nr_get_token_balance_20` expose NodeReal's custom indexed data directly to your LangChain graphs. Standard RPC nodes force you to iterate through millions of blocks to find token holders. These tools return the exact list in a single call. Your agent can take that list of addresses and immediately run `nr_get_asset_transfers` on each one to build a complete historical profile. It turns a massive data engineering problem into a basic tool-calling loop.

Setup guide

Set up Nodereal 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 Nodereal 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({
    "nodereal-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 Nodereal 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 NodeReal. 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 Nodereal 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 Nodereal MCP in LangChain

Install `langchain-mcp-adapters` and initialize a `MultiServerMCPClient`. Pass the HTTP transport URL for the server. Then call `client.get_tools()` and feed the list into your agent constructor.

Yes. The server exposes tools for both ecosystems simultaneously. Your agent looks at the user's request and picks `aptos_get_transactions` or `eth_get_logs` based on the context.

LangSmith tracks every MCP tool execution automatically. You will see the exact millisecond duration for calls like `eth_call` alongside the token usage for the agent's decision-making step.

They are. Tools like `nr_get_nft_inventory` and `nr_get_asset_transfers` are fully registered. Your agent calls them exactly like standard RPC endpoints.

The server only reads the specific transaction hashes or account addresses your agent passes to tools like `aptos_get_transaction_by_hash`. Vinkius runs this environment inside an isolated V8 sandbox, meaning memory is wiped after the session and no query data persists on the host.

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