How to Use the Dynamic (Web3 Auth) MCP in LangChain

Q: Can LangChain check wallet balances using Dynamic (Web3 Auth)?

Yes, the agent calls gettokenbalances to inspect user wallets. This tool returns active balances directly to your chain, letting the agent make routing decisions based on on-chain assets.

Q: How does LangChain trace Dynamic (Web3 Auth) tool calls?

LangSmith automatically tracks every call to tools like getuser or checksanctions. You get full visibility into latency, payload sizes, and execution paths for every Web3 authentication step.

Q: What happens when a Web3 session is revoked?

The agent triggers revokesession to kill the active token. Any subsequent tools requiring authentication will fail, stopping the chain from executing unauthorized actions.

LangChain agents verify Web3 wallets and manage Dynamic sessions directly inside your LLM run chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dynamic (Web3 Auth) MCP to LangChain

Create your Vinkius account to connect Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked Web3 compliance checks

The `check_sanctions` tool runs wallet addresses against blocklists inside your active LangChain run. Your agent checks compliance before triggering subsequent steps in the chain, stopping bad actors at the gate. Because this MCP server plugs into your LangChain adapters, the response feeds directly into your next run step. You get instant validation without writing custom middleware or manual API glue.

Track wallet data with this LangChain MCP Server

The `get_token_balances` tool fetches live token holdings for any user during a LangChain run. Your agent reads the balance payload to decide if a user qualifies for specific chain actions or gated prompts. LangSmith traces every token query, showing you the exact inputs and outputs. You see the raw balance data in your debug logs without guessing what the LLM received.

Kill active sessions on command

The `revoke_session` tool terminates active user sessions when your LangChain agent detects suspicious prompt behavior. If a user tries to exploit a chain, the agent shuts down their access immediately. This gives your LangChain pipelines active security controls. Instead of just flagging issues, your agent takes action by wiping the session token from the Dynamic environment.

Setup guide

Set up Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) 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({
    "dynamic-web3-auth-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 Dynamic (Web3 Auth) 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 Dynamic. 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 Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) MCP in LangChain

Install the adapters package and initialize the client with your Vinkius HTTP endpoint. This MCP setup lets you call the tools directly from your LangChain agent constructor to start querying Web3 sessions.

Yes, the agent calls `get_token_balances` to inspect user wallets. This tool returns active balances directly to your chain, letting the agent make routing decisions based on on-chain assets.

LangSmith automatically tracks every call to tools like `get_user` or `check_sanctions`. You get full visibility into latency, payload sizes, and execution paths for every Web3 authentication step.

The agent triggers `revoke_session` to kill the active token. Any subsequent tools requiring authentication will fail, stopping the chain from executing unauthorized actions.

Your Web3 wallet addresses, user profiles, and token balances never touch public LLM training sets. Vinkius runs the Dynamic server in a zero-trust V8 sandbox, passing data directly to your local LangChain execution environment without persistence.

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