How to Use the Blockscout MCP in Pydantic AI

Build type-safe blockchain agents with Pydantic AI and verified Blockscout data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blockscout MCP to Pydantic AI

Create your Vinkius account to connect Blockscout 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 Blockscout with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate blockchain data in Pydantic AI

Every response from `get_transaction` is checked against your Pydantic schemas. If the API returns a malformed object, your agent stops before it can make a bad call. This prevents silent errors where your agent might otherwise hallucinate field values. It forces a clean contract between your code and the blockchain.

Query total supply with Pydantic AI

Use `get_total_supply` to retrieve current coin metrics. Your agent can then use this data to perform automated calculations or generate reports. Because the output is validated, you know the numeric types are correct before they enter your business logic. It removes the risk of unexpected string-to-int conversion issues.

Fetch ABIs for Pydantic AI

Call `get_contract_abi` to get the interface for any verified contract. The server returns the ABI, and your Pydantic-backed agent validates the structure immediately. This allows your agent to construct function calls that are guaranteed to match the contract requirements. It is a safer way to interact with complex protocols.

Setup guide

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

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

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

You define your Pydantic models, and the MCP server maps the API output to them. This ensures the data you receive is exactly what your agent expects.

If a tool call fails, the server returns an error code that triggers your Pydantic validation failure. Your agent catches this and handles it via your defined logic.

You can restrict the exposed toolset in your agent definition. This limits the surface area and ensures your agent only has access to the functions you permit.

You use the standard HTTP transport with a Vinkius-issued token. The server remains external, keeping your agent logic decoupled from the data provider.

The server only processes the specific query you send and does not track your interaction history. It treats every request as a stateless, ephemeral event.

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