How to Use the NMKR Cardano MCP in Pydantic AI

Q: How do I connect the NMKR Cardano server to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset using the unified HTTP approach with your Vinkius endpoint URL. Pass this toolset to your Agent constructor.

Q: What happens if NMKR Cardano returns unexpected data to Pydantic AI?

The framework fails loudly. If a tool like listsplitaddresses returns an array that does not match your expected Pydantic model, the execution stops immediately with a clear type error.

Q: Can Pydantic AI track NMKR Cardano sub-customers?

Yes. The agent uses listsubcustomers to fetch the account list. You can define a Pydantic model for the expected sub-customer structure to ensure all required ID fields are present.

Q: Do I need to write custom models for the vesting addresses?

You define the expected output for listvestingaddresses in your agent's context. The MCP protocol handles the actual API request, while Pydantic guarantees the response matches your schema.

Q: How is my NFT metadata secured during execution?

The server processes your raw JSON files via validatenftmetadata entirely in memory. Vinkius routes the request through a stateless architecture that drops all context once the validation returns. No metadata files are cached or logged on our infrastructure.

Enforce strict runtime validation on your NMKR Cardano operations by connecting this MCP Server to your Pydantic AI agent.

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 Pydantic AI

Create your Vinkius account to connect NMKR Cardano to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Pydantic AI Validation

Silent data corruption kills automated workflows. When your agent calls `list_project_nfts` or `get_nft_details`, Pydantic AI validates the NMKR API response against your defined models. If the metadata schema changes unexpectedly, the agent throws a hard validation error and halts. This strict typing applies to your financial queries as well. Pulling data via `list_payout_wallets` guarantees you receive valid Cardano address strings. If the endpoint returns a null value or malformed text, Pydantic AI catches it before your downstream logic executes.

Guaranteed Metadata Integrity

You cannot afford to mint broken assets on mainnet. The agent runs `validate_nft_metadata` to verify your JSON structures against Cardano standards. Because Pydantic AI enforces type correctness, you know the agent is passing exactly the right payload to the validation tool. You can swap between Anthropic, OpenAI, or local models without rewriting this logic. The MCP framework ensures the tool inputs remain consistent regardless of which LLM decides to trigger the validation step.

Fail-Safe Asset Economics

Before starting any large operation, the system needs to verify its constraints. This MCP Server pulls `get_mint_coupon_balance` to check your NMKR credits and `get_project_counts` to see the current collection size. It also checks `get_project_discounts` to calculate fees. By combining these tools, the agent builds a complete cost profile for the drop. If the available coupons do not cover the projected cost, the Pydantic model rejects the execution path entirely.

Setup guide

Set up NMKR Cardano MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "nmkr-cardano-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NMKR Cardano tools.",
)

result = await agent.run("List recent NMKR Cardano transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` using the unified HTTP approach with your Vinkius endpoint URL. Pass this toolset to your Agent constructor.

The framework fails loudly. If a tool like `list_split_addresses` returns an array that does not match your expected Pydantic model, the execution stops immediately with a clear type error.

Yes. The agent uses `list_subcustomers` to fetch the account list. You can define a Pydantic model for the expected sub-customer structure to ensure all required ID fields are present.

You define the expected output for `list_vesting_addresses` in your agent's context. The MCP protocol handles the actual API request, while Pydantic guarantees the response matches your schema.

The server processes your raw JSON files via `validate_nft_metadata` entirely in memory. Vinkius routes the request through a stateless architecture that drops all context once the validation returns. No metadata files are cached or logged on our infrastructure.

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