How to Use the CardanoScan (Cardano Block Explorer API) MCP in Pydantic AI

Q: How do I configure CardanoScan (Cardano Block Explorer API) with Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP URL. Pass this toolset into your Agent constructor. Do not use the deprecated MCPServerHTTP method.

Q: Can Pydantic AI validate UTXO data from CardanoScan (Cardano Block Explorer API)?

Yes. When the agent calls gettransactionutxos, the framework validates the raw JSON against your Pydantic models. If the structure changes or fields are missing, the agent stops execution and throws an error.

Q: How do I handle pagination for stake pools via the MCP?

The listpools tool returns a paginated list. You define a loop in your agent logic to request subsequent pages until your Pydantic models capture the specific validator data you need.

Bring strict type safety to Cardano blockchain queries by connecting the CardanoScan MCP Server to your Pydantic AI workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CardanoScan (Cardano Block Explorer API) MCP to Pydantic AI

Create your Vinkius account to connect CardanoScan (Cardano 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 CardanoScan (Cardano Block Explorer API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Cardano Transactions in Pydantic AI

The `get_transaction` tool pulls block heights, fees, and deposit amounts for specific hashes directly from the MCP Server. Because Pydantic AI enforces strict schemas, any missing field from the explorer API triggers an immediate validation error rather than silently corrupting your database. Auditing fund flows requires exact precision. Your agent calls `get_transaction_utxos` to map the inputs and outputs, guaranteeing that the returned UTXO arrays match your predefined Python models before processing the accounting logic.

Query Stake Pools via MCP Server

The `list_pools` tool fetches active validators and their current performance metrics. Your agent can iterate through this paginated list, passing individual pool IDs to `get_pool` for deeper margin and pledge verification. Staking calculations depend on accurate epoch data. By combining `get_latest_epoch` with historical data from `get_epoch`, your system accurately projects reward distributions without hallucinating slot numbers.

Monitor Native Assets and Addresses

The `get_asset` tool retrieves minting policies and fingerprints for Cardano native tokens. If your agent expects an integer for total supply and receives a string, Pydantic AI fails loudly, stopping the workflow instantly. Wallet tracking relies on `get_address` to confirm balances and delegation status. Your system then pulls historical activity using `list_address_transactions`, ensuring every transfer record conforms to your strict data models.

Setup guide

Set up CardanoScan (Cardano 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": {
        "cardanoscan-cardano-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 CardanoScan (Cardano Block Explorer API) tools.",
)

result = await agent.run("List recent CardanoScan (Cardano 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 CardanoScan. 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 CardanoScan (Cardano 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 CardanoScan (Cardano Block Explorer API) MCP in Pydantic AI

Use the unified `MCPToolset` class pointing to your Vinkius HTTP URL. Pass this toolset into your Agent constructor. Do not use the deprecated `MCPServerHTTP` method.

Yes. When the agent calls `get_transaction_utxos`, the framework validates the raw JSON against your Pydantic models. If the structure changes or fields are missing, the agent stops execution and throws an error.

Pydantic AI is completely model-agnostic. You can route these block explorer queries through Anthropic, OpenAI, or a local Llama model running on your own hardware.

The `list_pools` tool returns a paginated list. You define a loop in your agent logic to request subsequent pages until your Pydantic models capture the specific validator data you need.

The server only touches public addresses and transaction hashes to read the chain. Vinkius isolates every single request in its own ephemeral container, ensuring no cross-contamination of your query parameters.

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