How to Use the Alchemy MCP in Pydantic AI

Q: How do I configure the Alchemy MCP Server with Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp". Create an MCPToolset pointing to your HTTP endpoint and pass it to the toolsets argument in your Agent.

Q: Why did Pydantic AI deprecate MCPServerHTTP for Alchemy?

The framework moved to a unified MCPToolset class for simpler configuration. This new approach handles both Streamable HTTP and SSE transports under one interface.

Enforce strict type validation on Ethereum data by connecting Alchemy to 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 Alchemy MCP to Pydantic AI

Create your Vinkius account to connect Alchemy 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 Alchemy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate wallet balances in Pydantic AI

Executing `get_wallet_balance` fetches the exact wei amount held by a specific address. If the MCP node returns a string instead of an integer, the framework throws a validation error immediately. Tracking ERC-20 assets happens via `get_token_balances`. Your agent receives the raw list, and Pydantic models ensure every contract address and balance matches your predefined schema before the code continues.

Parse receipts and NFT collections safely

The `get_transaction_receipt` tool pulls the execution logs for a given hash. Silent corruption is impossible here because the agent fails loudly if the receipt is missing required fields. Reading digital asset portfolios requires `get_owned_nfts`. Because this framework is model-agnostic, you can use a local model to parse the metadata while maintaining strict type safety.

Synchronize state via the MCP Server

The `get_latest_block_number` tool finds the current chain tip. This guarantees your agent operates on fresh data before attempting to resolve complex contract reads. Validating the node connection itself is done with `check_api_status`. The unified toolset approach manages the HTTP connection, ensuring your external server is actually reachable before the agent runs.

Setup guide

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

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

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

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Create an `MCPToolset` pointing to your HTTP endpoint and pass it to the `toolsets` argument in your Agent.

The framework moved to a unified `MCPToolset` class for simpler configuration. This new approach handles both Streamable HTTP and SSE transports under one interface.

The framework catches the mismatch during runtime validation. Instead of hallucinating a fix, the agent crashes with a clear error so you can debug the exact payload.

The node service must be running externally. Your Python code connects to it over HTTP, keeping the execution environments isolated.

This toolset never requests or processes private keys. It only accepts public identifiers like contract addresses and transaction hashes to read public state from the blockchain.

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