How to Use the Ankr (Web3 Node API) MCP in LangChain

Build multi-step Web3 reasoning chains in LangChain that pull live chain data and run transactions using the Ankr 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 Ankr (Web3 Node API) MCP to LangChain

Create your Vinkius account to connect Ankr (Web3 Node 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 Ankr (Web3 Node API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked Web3 queries with LangChain

LangChain agents can now chain raw blockchain reads directly into token evaluation steps. Your agent can run `ankr_getTokenPrice` to fetch the current market rate, feed that output into `eth_estimateGas` to calculate transaction costs, and then decide whether to proceed with a swap. It does this by passing state from one node to the next in your execution graph. You get full observability over this multi-step execution using LangSmith. Every time the agent queries `ankr_getAccountBalance` or checks a smart contract with `eth_call`, you see the exact payload, latency, and gas estimation in your trace logs. No more guessing why a transaction simulation failed or which RPC call timed out.

Multi-chain data aggregation in ReAct loops

Stop writing manual glue code to bridge Solana and EVM chains. This MCP Server lets your LangChain agent query `getAccountInfo` on Solana and immediately pivot to checking `ankr_getNFTsByOwner` on Ethereum within a single execution loop. The agent evaluates the results of each tool call dynamically to determine its next on-chain move. By declaring these Web3 tools inside your ReAct agent setup, you let the model choose the right RPC method based on the user's prompt. If a user asks to audit a wallet, the agent automatically executes `ankr_getInteractions` to map the history before calling specific balance tools.

Secure transaction assembly and simulation

Build reliable transaction pipelines by combining LangChain's state management with real-time network feedback. Your agent can verify an account's nonce with `eth_getTransactionCount`, fetch the latest blockhash via `getLatestBlockhash`, and simulate the transaction output using `eth_simulateV1` before committing any gas. If the simulation succeeds, the chain can route the payload to `eth_sendRawTransaction` or `sendTransaction` to write to the ledger. This sequence prevents failed on-chain transactions by making pre-flight validation a mandatory step in your agent's graph using the MCP Server's direct feedback.

Setup guide

Set up Ankr (Web3 Node 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 Ankr (Web3 Node 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({
    "ankr-web3-node-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 Ankr (Web3 Node 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 Ankr. 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 Ankr (Web3 Node 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 Ankr (Web3 Node API) MCP in LangChain

Install the adapters package and initialize the multi-server client pointing to your Vinkius endpoint. Call the tool generator function and pass those tools directly to your LangChain agent constructor.

Yes, the agent dynamically selects the correct tool based on the chain context. It can query `eth_getBalance` for Ethereum addresses and `getBalance` for Solana pubkeys in the same session.

LangSmith captures the exact inputs and outputs of every RPC tool call like `eth_call` or `ankr_getBlocks`. You can inspect the raw JSON-RPC payloads and latency to optimize your agent's decision steps.

The MCP Server itself is stateless, but you can use LangChain's memory or StateGraph to persist wallet addresses and transaction hashes. This allows the agent to reference previous `ankr_getAccountBalance` results in subsequent steps.

Vinkius runs the server in an isolated V8 sandbox where transaction payloads are processed ephemerally. Your private keys never touch the RPC node; tools like `eth_sendRawTransaction` only accept pre-signed transaction hex strings.

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