- VALIDATION
- ANALYSIS
- AUDIT
- HUMAN
Short answer
How can I test my Fusion query profiles using AI?
Your AI uses Fusion tools to pull existing profiles and run custom queries against your index. This lets you verify that vector rules and search logic produce the right results. You'll see exactly how your configurations behave in real time.
Validation outcomes.
What you'll find.
The AI handles the execution so you can focus on the results.
VALIDATION
Verified query logic
The AI runs the specific profiles you've built. You get to see if the logic holds up against real data.
ANALYSIS
Vector rule impact
Run custom queries to see how your vector settings change the relevance of the results.
AUDIT
Profile inventory
The AI pulls a list of all available profiles in your environment. This helps you keep track of what's active.
HUMAN
Manual tuning
The AI identifies discrepancies in results. You decide when to adjust the actual Fusion configuration.
The workflow
What your AI does when <the thing arrives>.
The AI acts as your testing interface for the Fusion environment.
Inventory profiles
The AI checks your Fusion environment to see which query profiles are currently configured and ready for testing.
lw.list_query_profilesExecute profiles
Your agent runs the specific profiles you want to validate to see the exact output they generate.
lw.query_searchTest custom logic
You can send specific, non-profile queries to test how new vector rules or filters behave in real time.
lw.post_custom_queryCompare results
The AI compares the output of different queries to help you spot shifts in relevance or ranking.
lw.query_search
Try it
Copy these to start.
Use these prompts to begin testing your Fusion setup.
Starting points
Replace the bracketed text with your specific profile names or query strings.
Lucidworks Fusion Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_jD2MOpvp0XAN4LgOxrkdAYw47AZunMSJvOVlZSCX/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Lucidworks Fusion capabilities are ready to use.
{
"mcpServers": {
"lucidworks-fusion-ai-search-discovery-mcp": {
"url": "https://edge.vinkius.com/vk_preview_jD2MOpvp0XAN4LgOxrkdAYw47AZunMSJvOVlZSCX/mcp"
}
}
}List all the query profiles currently available in my Fusion environment.
Run the 'customer_intent_v2' profile and show me the top results.
Execute a custom query for 'blue running shoes' using my custom vector rules.
Compare the results of the 'standard_search' profile against a custom query for 'premium gear'.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Lucidworks Fusion once, then ask.
One connection gives your AI access to your search environment. Your credentials stay encrypted and secure.
Connect Lucidworks Fusion to your AIFAQ
How this task behaves.
- 01
Can the AI change my query profiles?
No. The AI can only execute and read profiles. You must make all configuration changes manually in Fusion.
- 02
Can I delete search rules through the AI?
No. The tools only allow for listing, searching, and posting queries. Deletion is not supported.
- 03
How does the AI see my search results?
The AI receives the JSON response from the search execution and interprets the hits for you.
- 04
Does the AI have access to my raw index data?
The AI only sees the data returned by the specific queries you tell it to run.
- 05
Can I test vector search specifically?
Yes, by using custom queries that trigger your vector rules.
More questions about Lucidworks Fusion? The Connector page answers them. See everything the Lucidworks Fusion Connector can do
Connect Lucidworks Fusion to Claude, Cursor, ChatGPT & more
