How to Use the Meld MCP in LangChain

Q: How do I pass Meld tools to a LangChain agent?

Install the langchain-mcp-adapters package and initialize the client with the server's HTTP URL. Call gettools() on the client and pass that list directly to your agent constructor.

Q: Can I trace Meld tool execution in LangChain using LangSmith?

Yes, every tool call like listtransactions or getaccountinfo is tracked automatically. LangSmith captures the exact inputs, outputs, and latency of each financial query.

Let your LangChain agents query multi-chain wallet balances and trace live transaction histories across networks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Meld MCP to LangChain

Create your Vinkius account to connect Meld 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 Meld with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain multi-step crypto queries in LangChain.

This LangChain integration connects your workflows directly to the Meld digital asset API to fetch on-chain data. Your agent can run `list_wallets` to find active accounts, then instantly pass those addresses to `get_wallet_details` to extract balances without manual coding. This chaining pattern lets you build complex workflows that evaluate portfolios on the fly. You track exactly how token values flow through different networks by observing the inputs and outputs in LangSmith.

Feed live exchange rates to your ReAct agents.

The Meld real-time pricing tools let your LangChain agent pull live conversion metrics directly using `get_exchange_rates`. This MCP Server eliminates the need for hardcoded pricing data or stale database entries. When your agent detects a transaction via `list_transactions`, it immediately fetches the current rate to calculate the exact fiat value of that transfer. This keeps your financial logs accurate and automated.

Search assets and networks dynamically.

The Meld asset and network discovery tools allow your LangChain workflows to search for tokens dynamically. The agent invokes `search_assets` to locate specific tokens and uses `get_network` to verify chain compatibility before executing any analysis. By exposing `list_networks` to your agentic workflows, you let the LLM decide how to group and filter transactions based on the actual chains active in the user's portfolio.

Setup guide

Set up Meld 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 Meld 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({
    "meld-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 Meld 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 Meld. 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 Meld 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 Meld MCP in LangChain

Install the `langchain-mcp-adapters` package and initialize the client with the server's HTTP URL. Call `get_tools()` on the client and pass that list directly to your agent constructor.

Yes, every tool call like `list_transactions` or `get_account_info` is tracked automatically. LangSmith captures the exact inputs, outputs, and latency of each financial query.

You use the multi-server adapter to combine this financial MCP server with other tools. Your agent runs `get_wallet_details` and then sends the formatted results to a database tool in the same chain.

No, the MCP Server is stateless by default, making it easy to run concurrent queries. If you need persistent session context, use the client's session manager to keep track of active wallet addresses.

Vinkius runs this MCP server inside an isolated, zero-trust sandbox where your wallet addresses and transaction histories are never stored. The connection uses ephemeral tokens, ensuring your financial data is only visible to your local run.

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