How to Use the Blockchair (Universal Blockchain Search Engine & API) MCP in Pydantic AI

Q: How do I set up the Blockchair (Universal Blockchain Search Engine & API) MCP server in Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset class with your Vinkius HTTP endpoint. Pass the toolset directly to your Agent instance.

Q: How do I query ERC-20 tokens with this toolset?

Use geterc20tokenaddress to fetch token balances. The tool returns structured data that validates against your Pydantic models for safe balance tracking.

Run type-safe blockchain queries that fail loudly on unexpected data using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blockchair (Universal Blockchain Search Engine & API) MCP to Pydantic AI

Create your Vinkius account to connect Blockchair (Universal Blockchain Search Engine & 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 Blockchair (Universal Blockchain Search Engine & API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Address Validation with Pydantic AI

The `validate_address` and `get_address` tools check blockchain addresses and fetch their current balances. Pydantic AI validates the returned balance and UTXO structure against strict Python types at runtime. If the blockchain API returns an unexpected format, your system raises a validation error immediately. This prevents silent data corruption in your financial ledger with this MCP server.

Strict Block and Transaction Filtering

The `filter_blocks` and `filter_transactions` tools execute complex queries on historical blockchain data. The returned datasets are parsed directly into Pydantic models, ensuring every block height and fee matches your schema. This strict parsing is critical when calculating transaction fees. Your agent refuses to process data that fails validation, keeping your calculations accurate.

Secure Transaction Broadcasting

The `push_transaction` tool broadcasts raw hex transactions to the network. Pydantic AI validates the broadcast response schema before confirming the transaction status to your application. The MCP server returns structured responses that your code can rely on. This setup ensures you never miss a failed broadcast due to an unparsed error message.

Setup guide

Set up Blockchair (Universal Blockchain Search Engine & 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": {
        "blockchair-universal-blockchain-search-engine-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Blockchair (Universal Blockchain Search Engine & API) tools.",
)

result = await agent.run("List recent Blockchair (Universal Blockchain Search Engine & 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 Blockchair. 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 Blockchair (Universal Blockchain Search Engine & 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 Blockchair (Universal Blockchain Search Engine & API) MCP in Pydantic AI

Install pydantic-ai-slim[mcp] and use the MCPToolset class with your Vinkius HTTP endpoint. Pass the toolset directly to your Agent instance.

Your application will raise a validation error instantly. This loud failure prevents your agent from making decisions based on unverified or malformed blockchain data.

Yes. Pydantic AI is model-agnostic, meaning you can run these blockchain search tools with local models or commercial APIs in this MCP setup.

Use `get_erc20_token_address` to fetch token balances. The tool returns structured data that validates against your Pydantic models for safe balance tracking.

All API requests containing transaction hashes and account addresses run in a sandboxed V8 environment. Your queries are processed in-memory and destroyed immediately after execution.

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