How to Use the Blocknative (Ethereum Mempool API) MCP in Pydantic AI

Q: How do I initialize the Blocknative (Ethereum Mempool API) toolset in Pydantic AI?

Use the modern MCPToolset class pointing to the Vinkius HTTP MCP endpoint. Then, pass this toolset directly into your Agent constructor via the toolsets parameter.

Q: Will Pydantic AI validate the data returned by Blocknative (Ethereum Mempool API)?

Yes. The framework intercepts the output of getgasprices and validates it against the tool's defined schema, throwing a clear error if any field is missing or malformed.

Inject type-safe Ethereum gas price data into your Pydantic AI agents with zero risk of silent data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blocknative (Ethereum Mempool API) MCP to Pydantic AI

Create your Vinkius account to connect Blocknative (Ethereum Mempool 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 Blocknative (Ethereum Mempool API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Gas Estimation using Pydantic AI

When your agent queries the mempool, a single malformed payload can break your transaction logic. By connecting this MCP Server to Pydantic AI, every response from `get_gas_prices` is strictly validated against a typed schema before your code ever touches it. If the Blocknative API returns an unexpected data structure, the framework raises a validation error immediately. This prevents your agent from executing transactions based on corrupted or misaligned gas estimates.

Model-Agnostic Gas Monitoring

This integration doesn't lock you into a single LLM provider. You can use this with Anthropic, OpenAI, or a local model; the `get_gas_prices` tool behaves exactly the same way across all of them. The toolset translates the raw JSON from the Ethereum mempool into structured data your model can easily reason about. You get consistent, predictable outputs regardless of which model is currently driving your agent.

Unified Toolset Management

Stop dealing with deprecated HTTP client configurations. Pydantic AI uses the unified toolset to connect to external MCP servers over HTTP or SSE, simplifying your dependency chain. Your agent gets clean access to live gas price suggestions. This allows you to build reliable, production-ready DeFi automation tools that never fail silently due to unvalidated API responses.

Setup guide

Set up Blocknative (Ethereum Mempool 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": {
        "blocknative-ethereum-mempool-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Blocknative (Ethereum Mempool 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 Blocknative. 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 Blocknative (Ethereum Mempool 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 Blocknative (Ethereum Mempool API) MCP in Pydantic AI

Use the modern `MCPToolset` class pointing to the Vinkius HTTP MCP endpoint. Then, pass this toolset directly into your `Agent` constructor via the `toolsets` parameter.

Yes. The framework intercepts the output of `get_gas_prices` and validates it against the tool's defined schema, throwing a clear error if any field is missing or malformed.

Yes, but Pydantic AI requires the MCP Server to run as an external process. You connect to it using either Streamable HTTP or SSE transports.

Because the framework is strictly typed, your MCP client can catch connection and validation exceptions cleanly. This prevents any unpriced transactions from being sent if the API is unreachable.

The server only processes read-only requests for gas prices. No private transaction payloads or wallet addresses are ever sent, keeping your on-chain operations secure and anonymous.

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