How to Use the Nodereal MCP in Pydantic AI

Build type-safe blockchain agents with Pydantic AI and Nodereal to validate on-chain data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nodereal MCP to Pydantic AI

Create your Vinkius account to connect Nodereal 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 Nodereal with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe EVM State Validation

`eth_get_balance` retrieves the native balance of an address, returning a hex-encoded string. Pydantic AI validates this response against strict type definitions at runtime, ensuring your agent never processes corrupt data. If the API returns an unexpected format, the framework raises a validation error immediately. This strict typing extends to complex calls like `eth_call` and `eth_estimate_gas`. Your agent uses these tools to dry-run smart contract interactions. Because Pydantic AI enforces schemas, you avoid silent failures where an agent misinterprets a reverted transaction as a successful run.

Validated Aptos Chain Queries

`aptos_get_transaction_by_hash` fetches transaction details from the Aptos ledger. The MCP server delivers structured JSON payloads that Pydantic AI maps directly to Python models. This guarantees that fields like transaction sequence numbers and event payloads match your exact specifications before your agent logic consumes them. Your agent can also run `aptos_get_transactions` to paginate through history or `aptos_get_account` to verify sequence numbers. The framework ensures that data from these calls is clean. No more writing manual try-except blocks to catch missing dictionary keys in raw API responses.

Strict Token Indexing with Pydantic AI

`nr_get_token_balance_20` returns ERC20 token balances validated against Pydantic models. This ensures that token balances, decimals, and addresses are correctly typed before your agent makes financial decisions. The server offloads the indexing complexity, while Pydantic AI guarantees the data's structural integrity. For NFT tracking, the agent runs `nr_get_nft_inventory` and `nr_get_nft_holders`. The output is parsed into structured models, making it easy to build automated portfolio checkers. This setup works with any LLM provider supported by Pydantic AI, keeping your code model-agnostic.

Setup guide

Set up Nodereal 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": {
        "nodereal-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Nodereal 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 NodeReal. 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 Nodereal 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 Nodereal MCP in Pydantic AI

Install the slim package with MCP support, then use the toolset constructor with your Vinkius HTTP endpoint. Pass this toolset into the toolsets argument of your Pydantic AI Agent. The framework automatically imports and validates all 24 tools.

The framework raises a validation error at runtime, halting execution before your agent can act on bad data. This prevents issues like treating an invalid transaction receipt from a block query as a confirmed transfer.

Yes. Pydantic AI is model-agnostic. You can pair this server with local models or commercial APIs while maintaining the same strict validation rules for tools like block number queries or Aptos ledger info.

Yes. The server exposes the log retrieval tool. Your agent can query logs with specific topic filters, and Pydantic AI will validate the returned log array structure to ensure your application parses the contract events correctly.

The server only reads public chain data like account resources, block details, and token balances. Vinkius runs the toolset inside a stateless V8 runtime that wipes memory after execution, meaning your credentials and query payloads are never stored.

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