How to Use the Aurorascan (Aurora Network L2 Block Explorer API) MCP in Pydantic AI

Q: How do I setup Aurorascan (Aurora Network L2 Block Explorer API) with Pydantic AI?

Install "pydantic-ai-slimmcp". Use the unified MCPToolset class with your HTTP endpoint. Add it to the toolsets list when configuring your agent.

Q: How does Pydantic AI handle Aurorascan (Aurora Network L2 Block Explorer API) validation errors?

It fails loudly. If the API returns a string for proxygasprice and your model expects an integer, the agent throws a runtime validation error immediately.

Q: Should I use MCPServerHTTP or MCPToolset?

Always use MCPToolset. The older MCPServerHTTP class is deprecated in recent versions of the framework.

Type-safe Aurora L2 blockchain queries that fail loudly in your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aurorascan (Aurora Network L2 Block Explorer API) MCP to Pydantic AI

Create your Vinkius account to connect Aurorascan (Aurora Network L2 Block Explorer API) 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 Aurorascan (Aurora Network L2 Block Explorer API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Balance Verification

Financial data requires absolute precision. When your agent calls `get_balance` or `get_balance_multi`, Pydantic AI validates the returned wei amounts against your defined schemas. If the API returns a string when you expect an integer, the system throws a validation error immediately. You instantiate the connection using `MCPToolset`. This guarantees your downstream trading logic never executes on hallucinated or malformed balance data. The agent catches the error, retries the request, or alerts a human operator.

Check ERC20 Token Supplies

Auditing token economics means verifying total circulation. The agent runs `get_token_supply` to pull the exact number of tokens minted for a specific contract address. It then uses `get_eth_supply` to compare that custom token against the native ether supply on Aurora. Because Pydantic AI is model-agnostic, you can swap out the underlying LLM without changing your verification logic. The strict type boundaries ensure that whether you use Anthropic or a local model, the supply numbers always match your expected data structures.

Monitor Contract Execution

Failed transactions cost money and stall automated workflows. Your agent calls `get_status` to check if a specific contract execution succeeded. For deeper debugging, `get_tx_receipt_status` confirms exactly how the transaction settled on the L2 network. The framework parses these boolean status flags perfectly. Instead of the agent guessing if a transaction went through based on natural language text, it relies on strict true/false returns enforced by your Pydantic models.

Setup guide

Set up Aurorascan (Aurora Network L2 Block Explorer API) 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": {
        "aurorascan-aurora-network-l2-block-explorer-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Aurorascan (Aurora Network L2 Block Explorer API) tools.",
)

result = await agent.run("List recent Aurorascan (Aurora Network L2 Block Explorer API) 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 Aurorascan. 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 Aurorascan (Aurora Network L2 Block Explorer API) 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 Aurorascan (Aurora Network L2 Block Explorer API) MCP in Pydantic AI

Install `"pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class with your HTTP endpoint. Add it to the `toolsets` list when configuring your agent.

Yes. The framework is model-agnostic. As long as your local model supports function calling, it can request data from the server.

It fails loudly. If the API returns a string for `proxy_gas_price` and your model expects an integer, the agent throws a runtime validation error immediately.

Always use `MCPToolset`. The older `MCPServerHTTP` class is deprecated in recent versions of the framework.

The server handles RPC proxy calls and smart contract ABIs inside a zero-trust execution environment. Your specific query parameters disappear the moment the connection closes.

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