How to Use the Lucidworks Fusion (AI Search & Discovery) MCP in OpenAI Agents SDK

Q: How does Lucidworks Fusion (AI Search & Discovery) handle vector search within OpenAI Agents SDK?

Your agent invokes lw.querysearch to execute neural search queries. It maps the user's intent to vector spaces defined in your query profiles, returning raw documents with precise relevance scores.

Q: Can I run custom Solr JSON queries using this MCP Server?

Yes. The lw.postcustomquery tool lets your agent send raw JSON logic to override default search profiles. This is ideal when you need deep control over Solr vectors.

Q: How do I index new documents dynamically in Lucidworks Fusion (AI Search & Discovery) with OpenAI Agents SDK?

You use the lw.indexdocuments tool to push raw payloads directly into your collections. The server bypasses intermediate pipelines, updating your index immediately.

Q: What is the best way to verify active ML training jobs?

Run lw.listjobs through your agent. It returns a list of running and scheduled jobs, allowing your agent to wait for a model to finish training before running new evaluations.

Q: How does Lucidworks Fusion (AI Search & Discovery) keep search telemetry data private in OpenAI Agents SDK?

This MCP Server passes telemetry signals via lw.postsignal through a secure V8 isolate sandbox. Raw clickstream and search query telemetry are encrypted in transit and never stored on the Vinkius gateway.

Run enterprise search pipelines directly from your production OpenAI Agents SDK workflows using managed MCP connections.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lucidworks Fusion (AI Search & Discovery) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run hybrid search from OpenAI Agents SDK

`lw.query_search` lets your agent execute semantic vector queries directly against your Fusion collections. It resolves precise AI vector rules on the fly, matching strict profile logics to fetch relevant records without manual keyword mapping. You configure the connection using the MCP HTTP transport class. The agent automatically discovers this tool during runtime, letting you map Solr vector overrides instantly via `lw.post_custom_query` when default profiles fall short.

Track user engagement with signal logging

`lw.post_signal` sends behavioral telemetry back to your search cluster to update machine learning relevance models. Your agent logs clicks, cart additions, or custom events to ensure the next search run is sharper. Managing these background pipelines requires visibility. Use `lw.list_jobs` to check active indexing or training tasks, keeping your search index synchronized with user actions.

Manage collections and query profiles dynamically

`lw.list_collections` exposes your active Fusion collections to the agent. This allows the system to route search queries dynamically based on user context rather than hardcoding endpoints. The agent verifies routing rules via `lw.list_query_profiles` to ensure requests hit the correct pipeline. If your app needs strict sorting, `lw.query_sorted` applies parameters like date or price before the agent processes the payload.

Setup guide

Set up Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Lucidworks Fusion (AI Search & Discovery) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Lucidworks Fusion (AI Search & Discovery) 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="Lucidworks Fusion (AI Search & Discovery) Agent",
            instructions="You have access to Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion. 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 Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) MCP in OpenAI Agents SDK

Your agent invokes `lw.query_search` to execute neural search queries. It maps the user's intent to vector spaces defined in your query profiles, returning raw documents with precise relevance scores.

Yes. The `lw.post_custom_query` tool lets your agent send raw JSON logic to override default search profiles. This is ideal when you need deep control over Solr vectors.

You use the `lw.index_documents` tool to push raw payloads directly into your collections. The server bypasses intermediate pipelines, updating your index immediately.

Run `lw.list_jobs` through your agent. It returns a list of running and scheduled jobs, allowing your agent to wait for a model to finish training before running new evaluations.

This MCP Server passes telemetry signals via `lw.post_signal` through a secure V8 isolate sandbox. Raw clickstream and search query telemetry are encrypted in transit and never stored on the Vinkius gateway.

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