How to Use the Blastscan (Blast Network Explorer) MCP in Pydantic AI

Q: How do I set up Blastscan (Blast Network Explorer) with Pydantic AI?

Install pydantic-ai-slimmcp and define your MCPToolset with the Vinkius MCP server URL. Pass this toolset into your Agent constructor to give your model type-safe access to Blast data.

Q: Can Pydantic AI validate block countdowns from Blastscan (Blast Network Explorer)?

Yes, when your agent calls getblockcountdown, Pydantic AI validates the estimated time response against its internal models. If the block number format is invalid, the framework catches it immediately.

Q: How does Pydantic AI handle raw JSON-RPC data from Blastscan (Blast Network Explorer)?

When your agent calls low-level tools like proxyethgetblockbynumber, Pydantic AI maps the raw JSON response to typed Python objects. This prevents your agent from failing silently when parsing complex block structures.

Q: Is the MCPServerHTTP class still supported in Pydantic AI?

No, MCPServerHTTP is deprecated in Pydantic AI. You should use the unified MCPToolset class to connect to your external Blastscan MCP server over HTTP or SSE.

Q: How does Blastscan (Blast Network Explorer) handle the privacy of my smart contract storage in Pydantic AI?

All requests for contract storage via proxyethgetstorageat are executed statelessly inside our ephemeral V8 sandbox. Vinkius does not store any on-chain queries, ensuring your contract analysis remains completely private.

Validate Blast blockchain data and smart contract states with type-safe tools in 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 Blastscan (Blast Network Explorer) MCP to Pydantic AI

Create your Vinkius account to connect Blastscan (Blast Network Explorer) 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 Blastscan (Blast Network Explorer) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Blast transaction receipts using Pydantic AI

The `get_transaction_receipt_status` and `get_transaction_status` tools allow your Pydantic AI agent to verify execution statuses on the Blast network with strict type guarantees. If the Blast API returns an unexpected payload, Pydantic AI raises a validation error instantly instead of letting your agent hallucinate. You initialize this by passing the `MCPToolset` pointing to your Vinkius HTTP endpoint into your Pydantic AI `Agent`. This ensures that every transaction hash checked by the agent strictly matches your defined Python schemas.

Type-safe storage reads with this MCP Server

This MCP Server provides the `proxy_eth_getstorageat` and `proxy_eth_getcode` tools to read raw smart contract storage and bytecode directly from Blast. Pydantic AI validates these low-level hex strings at runtime, ensuring your agent never processes corrupted blockchain data. By using the unified `MCPToolset` class, you connect your agent to the external Vinkius server via SSE or HTTP. The agent can then safely parse storage slots without silent failures.

Fetch validated contract source code on Blast

The `get_contract_source_code` tool retrieves verified Solidity code from the Blast network for analysis by your Pydantic AI agent. Because Pydantic AI enforces strict data models, the returned code strings are validated before your agent even reads them. This setup prevents the agent from choking on malformed source code or unexpected API responses. You get clean, typed data fed directly into your security analysis pipelines.

Setup guide

Set up Blastscan (Blast Network Explorer) 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": {
        "blastscan-blast-network-explorer-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Blastscan (Blast Network Explorer) 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 Blastscan. 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 Blastscan (Blast Network Explorer) 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 Blastscan (Blast Network Explorer) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and define your `MCPToolset` with the Vinkius MCP server URL. Pass this toolset into your `Agent` constructor to give your model type-safe access to Blast data.

Yes, when your agent calls `get_block_countdown`, Pydantic AI validates the estimated time response against its internal models. If the block number format is invalid, the framework catches it immediately.

When your agent calls low-level tools like `proxy_eth_getblockbynumber`, Pydantic AI maps the raw JSON response to typed Python objects. This prevents your agent from failing silently when parsing complex block structures.

No, `MCPServerHTTP` is deprecated in Pydantic AI. You should use the unified `MCPToolset` class to connect to your external Blastscan MCP server over HTTP or SSE.

All requests for contract storage via `proxy_eth_getstorageat` are executed statelessly inside our ephemeral V8 sandbox. Vinkius does not store any on-chain queries, ensuring your contract analysis remains completely private.

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