How to Use the Aptoscan (Aptos Blockchain Explorer API) MCP in Pydantic AI

Q: What happens if the Aptoscan API returns an unexpected format to my Pydantic AI agent?

Your agent will stop and raise a ValidationError immediately. This is the core benefit—it prevents your application from acting on incorrect or malformed data from the blockchain API, avoiding silent failures.

Q: What's the new way to add an MCP Server in Pydantic AI?

Use the unified MCPToolset. Just pass your Vinkius server URL to its constructor, like MCPToolset("http://..."). The older MCPServerHTTP class is deprecated.

Build type-safe Aptos blockchain agents with Pydantic AI that never fail silently.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aptoscan (Aptos Blockchain Explorer API) MCP to Pydantic AI

Create your Vinkius account to connect Aptoscan (Aptos Blockchain 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 Aptoscan (Aptos Blockchain Explorer API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Responses You Can Trust

Stop worrying about bad data from APIs. With Pydantic AI, every response from the Aptoscan tools is automatically validated against a strict Pydantic model. You know exactly what data structure you're getting back from calls like `get_token_data` or `get_account_resources`. If the API ever returns a malformed response, an extra field, or a wrong data type, your code doesn't just stumble on. It raises a `ValidationError` immediately. This means no silent data corruption, just predictable, reliable agents.

Use Any LLM You Want

Your choice of LLM shouldn't be tied to your tools. Pydantic AI is model-agnostic. You can build your type-safe Aptoscan agent using models from OpenAI, Anthropic, Google, or even a local model running on your machine. The correctness guarantee comes from Pydantic, not the LLM. This gives you the freedom to swap out the brain of your agent anytime without having to rewrite your data validation logic. The Aptoscan toolset will work the same way.

A Clean Fit for Your Python Code

Adding the Aptoscan tools to your Pydantic AI agent feels natural. You're not fighting the framework. Just instantiate `MCPToolset` with the Vinkius URL and add it to your agent's `toolsets` list. It’s a one-liner to give your agent access to all ten blockchain tools, from `get_transaction_by_hash` to `get_account_modules`. This clean integration means you spend less time on boilerplate and more time defining what your agent should actually do with the Aptos data.

Setup guide

Set up Aptoscan (Aptos Blockchain 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": {
        "aptoscan-aptos-blockchain-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 Aptoscan (Aptos Blockchain Explorer API) tools.",
)

result = await agent.run("List recent Aptoscan (Aptos Blockchain 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 Aptoscan. 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 Aptoscan (Aptos Blockchain 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 Aptoscan (Aptos Blockchain Explorer API) MCP in Pydantic AI

It validates every API response against a Pydantic model at runtime. If the data from a tool like `get_account_balance` doesn't match the expected schema, your agent will raise a `ValidationError` instead of processing bad data.

Yes. Pydantic AI is model-agnostic. As long as you have a compatible instructor client for your local model, you can use the same `MCPToolset` for Aptoscan without changing any tool-related code.

Your agent will stop and raise a `ValidationError` immediately. This is the core benefit—it prevents your application from acting on incorrect or malformed data from the blockchain API, avoiding silent failures.

Use the unified `MCPToolset`. Just pass your Vinkius server URL to its constructor, like `MCPToolset("http://...")`. The older `MCPServerHTTP` class is deprecated.

The server fetches public data from the Aptos blockchain, such as transaction hashes and block heights. Vinkius ensures security by running each MCP Server in an ephemeral container that is destroyed after use. The actual data validation against your Pydantic models happens within your own application's memory.

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