How to Use the NMKR Cardano MCP in LangChain

Q: How do I integrate the NMKR Cardano MCP server with my LangChain agent?

Install langchain-mcp-adapters. Use MultiServerMCPClient to connect to the Vinkius endpoint, then pass the NMKR tools to your createagent function.

Q: Can LangChain track the latency of NMKR Cardano API calls?

Yes. Every time your agent calls a tool like getprojectcounts, LangSmith logs the request. You see exact execution times and tool inputs.

Q: How do I manage multiple projects across different accounts?

Run listsubcustomers to fetch the account hierarchy. Pass that context into your agent's session state so it knows which project ID to query next.

Build LangChain ReAct agents that manage Cardano NFTs, track minting coupons, and validate metadata directly through NMKR Studio.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NMKR Cardano MCP to LangChain

Create your Vinkius account to connect NMKR Cardano 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 NMKR Cardano with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Cardano metadata in pipelines

You use `validate_nft_metadata` as the first link in a chain to check raw JSON before paying on-chain fees. If the schema fails, the agent stops the pipeline immediately. This prevents broken assets from hitting the network. When validation passes, the output feeds straight into `get_mint_coupon_balance`. The agent checks if you have enough credits to mint. LangSmith traces the exact token usage and latency for both NMKR API calls.

Route revenue splits with this MCP Server

Give your agent access to `list_split_addresses` and `list_payout_wallets` to pull the active configuration directly from NMKR Studio. Hardcoding payout logic is a mistake. The agent reads the live routing table instead. When a project sells out, the chain triggers `get_project_counts`. The agent verifies the final asset metrics. It then outputs a formatted report of which sub-customers get paid based on the live split data.

Combine NMKR data with external databases

A LangChain agent can pull active discounts using `get_project_discounts` and cross-reference them with your internal Postgres database. You do not have to isolate your Cardano logic. The agent handles the external API call and the local database lookup in one step. Need specific asset details? The agent runs `list_project_nfts`, picks a specific token, and runs `get_nft_details`. The output gets formatted and sent to your Slack channel via another tool in the same chain.

Setup guide

Set up NMKR Cardano 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 NMKR Cardano 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({
    "nmkr-cardano-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 NMKR Cardano 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 NMKR. 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 NMKR Cardano 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 NMKR Cardano MCP in LangChain

Install `langchain-mcp-adapters`. Use `MultiServerMCPClient` to connect to the Vinkius endpoint, then pass the NMKR tools to your `create_agent` function.

Yes. Every time your agent calls a tool like `get_project_counts`, LangSmith logs the request. You see exact execution times and tool inputs.

That depends on your prompt. ReAct agents look at the descriptions for tools like `list_vesting_addresses` and decide the execution order based on the user's goal.

Run `list_subcustomers` to fetch the account hierarchy. Pass that context into your agent's session state so it knows which project ID to query next.

The MCP standard enforces strict isolation. When your agent fetches `list_split_addresses`, that routing data only exists in memory during the chain execution. Vinkius runs the server in an ephemeral V8 Isolate, meaning your payout configurations disappear the moment the session ends.

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