How to Use the BlockCypher (Multi-chain Blockchain Developer API) MCP in Pydantic AI

Q: How do I register the BlockCypher (Multi-chain Blockchain Developer API) MCP Server in Pydantic AI?

Initialize MCPToolset with your Vinkius HTTP endpoint. Pass this toolset instance inside the toolsets list when defining your Pydantic AI Agent.

Q: Does this setup support the deprecated HTTP server class?

No, you should use the unified MCPToolset approach. The older MCP Server HTTP class is deprecated and may cause integration issues in newer versions of the library.

Build type-safe blockchain agents with Pydantic AI that validate BlockCypher data schemas at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BlockCypher (Multi-chain Blockchain Developer API) MCP to Pydantic AI

Create your Vinkius account to connect BlockCypher (Multi-chain Blockchain Developer 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 BlockCypher (Multi-chain Blockchain Developer API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe contract interactions via Pydantic AI

Your Pydantic AI agent uses `call_eth_contract_method` to interact with Ethereum contracts, validating every returned byte against strict Pydantic models. If the contract returns an unexpected format, the framework raises a validation error immediately. This prevents your agent from parsing corrupted contract data or acting on hallucinated transaction states. The runtime validation ensures that only structurally sound blockchain payloads reach your core application logic.

Validate transaction structures before broadcasting

The `new_transaction` tool generates a raw transaction skeleton that your agent can inspect and structure using typed models. By validating the transaction skeleton at runtime, you ensure that fee estimates and output addresses match your exact specifications. Once validation passes, the agent uses `send_transaction` to broadcast the signed payload. Any API errors or network issues are caught instantly by the framework's strict error-handling boundaries.

Strict schema validation on this MCP Server's outputs

This MCP Server delivers structured JSON payloads for tools like `get_blockchain` and `get_address_balance`. Pydantic AI parses these payloads into strongly typed Python objects, eliminating silent failures caused by API updates. If the blockchain state changes or returns an unexpected field, the toolset raises a loud runtime error. This guarantees that your agent never operates on malformed balance or block height data.

Setup guide

Set up BlockCypher (Multi-chain Blockchain Developer 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": {
        "blockcypher-multi-chain-blockchain-developer-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to BlockCypher (Multi-chain Blockchain Developer API) tools.",
)

result = await agent.run("List recent BlockCypher (Multi-chain Blockchain Developer 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 BlockCypher. 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 BlockCypher (Multi-chain Blockchain Developer 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 BlockCypher (Multi-chain Blockchain Developer API) MCP in Pydantic AI

Initialize `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset instance inside the `toolsets` list when defining your Pydantic AI Agent.

The framework immediately raises a validation error instead of passing dirty data to the model. This protects your agent from making decisions based on incomplete block or transaction data.

Yes, because Pydantic AI is model-agnostic, you can use these blockchain tools with local models or commercial LLMs while maintaining strict type safety.

No, you should use the unified `MCPToolset` approach. The older MCP Server HTTP class is deprecated and may cause integration issues in newer versions of the library.

Your BlockCypher API tokens and address query parameters are processed in an ephemeral, isolated V8 sandbox. This zero-trust architecture ensures your sensitive keys never touch the LLM context or log files.

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