How to Use the Blur (NFT Trading Marketplace API) MCP in Pydantic AI

Q: How do I configure the Blur (NFT Trading Marketplace API) in Pydantic AI?

Install pydantic-ai-slimmcp and initialize MCPToolset with your Vinkius server URL. Pass this toolset to your Agent constructor to expose tools like getcollectionfloor over MCP.

Q: Why does this setup use the unified MCPToolset instead of older HTTP classes?

The unified MCPToolset is the current standard in Pydantic AI, replacing deprecated classes like MCPServerHTTP. It simplifies your imports and ensures compatibility with both SSE and streamable HTTP transports.

Build type-safe, validated NFT trading workflows on Blur with runtime schema verification 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 Blur (NFT Trading Marketplace API) MCP to Pydantic AI

Create your Vinkius account to connect Blur (NFT Trading Marketplace 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 Blur (NFT Trading Marketplace API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe NFT Metadata Parsing

The `get_asset` tool pulls specific NFT metadata and listings, validating the raw JSON response against strict Pydantic models at runtime. If the marketplace API structure changes unexpectedly, your application fails immediately with a validation error rather than passing corrupt data to your LLM. This strict validation prevents silent failures in production. Your agent always receives predictable data structures, allowing you to write clean, typed Python code around floor prices and token attributes.

Validated Bid and Ask Execution

Your agent uses `create_bid` and `create_ask` to execute trades on Blur with complete type safety. Every parameter, from the target collection address to the bid price in ETH, is verified against the defined schema before the payload leaves your environment. This setup eliminates formatting errors that cause API rejections. Because Pydantic AI is model-agnostic, you get this strict validation layer whether your underlying agent runs on OpenAI, Anthropic, or a local model.

Unified MCP Server Integration

This MCP Server integrates with your codebase using the unified `MCPToolset` class, bypassing deprecated HTTP initialization methods. You pass the Vinkius server URL directly to the toolset and register it with your agent in a single line of code. The toolset handles the underlying SSE or Streamable HTTP transport protocols automatically. Your agent gets instant, programmatic access to `get_collection_floor` and other tools while maintaining clean, readable code.

Setup guide

Set up Blur (NFT Trading Marketplace 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": {
        "blur-nft-trading-marketplace-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Blur (NFT Trading Marketplace 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 Blur. 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 Blur (NFT Trading Marketplace 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 Blur (NFT Trading Marketplace API) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` with your Vinkius server URL. Pass this toolset to your `Agent` constructor to expose tools like `get_collection_floor` over MCP.

The framework validates the API payload against strict Pydantic schemas at runtime. If there is a schema mismatch, it raises a validation error instantly, preventing your agent from hallucinating or acting on corrupt marketplace data.

Yes. Pydantic AI is completely model-agnostic, meaning you can connect these marketplace tools to local models or alternative provider APIs while maintaining identical type validation for your bids and listings.

The unified `MCPToolset` is the current standard in Pydantic AI, replacing deprecated classes like `MCPServerHTTP`. It simplifies your imports and ensures compatibility with both SSE and streamable HTTP transports.

Vinkius runs the server inside a zero-trust, isolated sandbox environment. Your transaction payloads, including bids and asks, are transmitted securely over HTTPS, and no historical marketplace data or wallet details are persisted on the host.

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