How to Use the Doofinder MCP in Pydantic AI

Q: Does Doofinder and Pydantic AI support faceted search?

Yes. The searchfiltered tool returns data that fits your model, allowing for easy filtering based on your defined product attributes.

Q: Can I verify my index configuration?

Yes, use getindices to check your current catalog status. It returns a structured object that your agent can validate for correctness.

Build type-safe search agents with Pydantic AI and Doofinder. Validate every search response against your domain models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Doofinder MCP to Pydantic AI

Create your Vinkius account to connect Doofinder 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 Doofinder with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe search with Pydantic AI

Every response from `search_keyword` or `search_filtered` is validated against your Pydantic models. If the API returns unexpected data, your agent stops immediately. This prevents silent errors in your search logic. You get reliable, typed data in every turn of the conversation.

Precise data retrieval

Use `get_items` to pull specific product records into your agent's context. Because it's validated, you know exactly what fields you're working with. Combine this with `search_sorted` to order your results by price or popularity. Your agent follows your strict business requirements for every query.

Analytics-driven agent logic

The `get_stats` tool provides performance metrics that your agent validates before taking action. It ensures your optimization logic is based on accurate, clean data. Use `suggest` for autocomplete tasks. The type-safe response ensures your UI only receives valid suggestions for the end user.

Setup guide

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

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

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

Define your Pydantic models and use the MCPToolset. The agent will automatically validate the output of `search_keyword` against your schema.

Yes. The `search_filtered` tool returns data that fits your model, allowing for easy filtering based on your defined product attributes.

We enforce strict validation on all incoming data packets. This ensures that only authorized product catalog information is processed by your agent.

Your agent will throw a validation error rather than hallucinating fields. This makes it easy to spot and fix schema mismatches immediately.

Yes, use `get_indices` to check your current catalog status. It returns a structured object that your agent can validate for correctness.

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

Mastra AI sdk-typescript

Start using the Doofinder MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started