How to Use the Doofinder MCP in OpenAI Agents SDK

Q: Can Doofinder and OpenAI Agents SDK handle filtered queries?

Yes. The searchfiltered tool lets you pass specific facets to the agent. It restricts the results to exactly what the user needs.

Q: How do I debug search results in my agent?

Use getitems to inspect the raw data returned by your search engine. It helps you verify that your index matches your expectations.

Connect your OpenAI Agents SDK production system to Doofinder. Search, suggest, and audit your store data with native tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect Doofinder to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full search control for OpenAI Agents SDK

Your agent can now execute precise queries using `search_keyword` and `search_filtered` to pull exact product data. It keeps your search logic tight and avoids unnecessary data bloat. By using `search_sorted` and `search_pagination`, your agent manages large result sets efficiently. It handles the heavy lifting so your production system stays fast and responsive.

Predictive search integration

The `suggest` tool allows your agent to offer real-time autocomplete results to your users. It turns basic search bars into active, helpful shopping assistants. It connects directly into your agent's decision loop. Your system identifies user intent faster and improves conversion without extra code.

Audit and monitor search analytics

Use `get_stats` to feed search performance data directly into your agent's monitoring logic. You get clear visibility into how users interact with your catalog. Combine this with `get_indices` and `get_items` to inspect your current setup. Your agent verifies that your product data matches the actual search results.

Setup guide

Set up Doofinder MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Doofinder tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Doofinder tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Doofinder tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Doofinder Agent",
            instructions="You have access to Doofinder tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You instantiate the server via the SDK and let it auto-discover the tools. Once connected, call the `search_keyword` tool directly from your agent's execution flow.

Yes. The `search_filtered` tool lets you pass specific facets to the agent. It restricts the results to exactly what the user needs.

Your product data remains within your controlled environment. We only access the specific catalog indices required to return search results.

Use `get_items` to inspect the raw data returned by your search engine. It helps you verify that your index matches your expectations.

Not at all. You provide the endpoint and the SDK handles the tool registration. It's built for production environments that need to move fast.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.