How to Use the Lucidworks Fusion (AI Search & Discovery) MCP in Cursor

Q: How does Cursor use Lucidworks Fusion (AI Search & Discovery) to test query profiles?

Cursor uses the MCP Server to call lw.listqueryprofiles to find your active query routing rules. From there, it can execute test queries directly against those profiles to see how results are returned.

Q: Can I index sample documents into Lucidworks Fusion (AI Search & Discovery) from Cursor?

Yes, you can push test payloads directly. Cursor calls lw.indexdocuments to index documents, letting you verify your parsing pipelines instantly.

Q: How do I configure Lucidworks Fusion (AI Search & Discovery) in Cursor?

Add the server details to your .cursor/mcp.json file in your project root. Once configured, Cursor's native MCP integration handles the rest when you enable Agent mode in chat.

Q: Can I run custom Solr vector queries using this setup?

Yes, the server includes lw.postcustomquery. This tool lets Cursor send custom JSON payloads to override default search parameters during development.

Write search code that works with live Lucidworks Fusion (AI Search & Discovery) data in Cursor.

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 Cursor

Create your Vinkius account to connect Lucidworks Fusion (AI Search & Discovery) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Test search logic while writing code in Cursor

Running real queries with `lw.query_search` lets you verify your code against live search results instead of writing mock data. This gives you instant confidence in your integration logic. If you need to verify how filters affect your query response, `lw.query_filtered` lets your agent pull back properties tied to active account logic. You get real payloads to shape your frontend components instantly.

Sync search telemetry directly with your codebase

Testing telemetry logging is straightforward with the `lw.post_signal` tool, which sends real events to your Fusion instance from the editor. Your agent uses these interactions to validate your analytics pipeline. To make sure those signals are actually training your search models, your agent can run `lw.list_jobs` to monitor active ML runs. This keeps your feedback loop tight while you write your analytics code.

Inspect index schemas without leaving your editor

Your agent uses `lw.list_collections` to pull your active index configurations straight into your Cursor sidebar so you don't have to switch windows. Having this schema data at your fingertips makes writing database mappings fast. If you need to check how your data is being parsed, `lw.list_index_profiles` reveals the active array rules. Running `lw.index_documents` allows you to test how your document ingestion code handles raw payloads.

Setup guide

Set up Lucidworks Fusion (AI Search & Discovery) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Lucidworks Fusion (AI Search & Discovery) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Lucidworks Fusion (AI Search & Discovery) transactions." If the MCP tools are loaded correctly, Cursor will call the Lucidworks Fusion (AI Search & Discovery) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "lucidworks-fusion-ai-search-discovery-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Cursor uses the MCP Server to call `lw.list_query_profiles` to find your active query routing rules. From there, it can execute test queries directly against those profiles to see how results are returned.

Yes, you can push test payloads directly. Cursor calls `lw.index_documents` to index documents, letting you verify your parsing pipelines instantly.

Add the server details to your `.cursor/mcp.json` file in your project root. Once configured, Cursor's native MCP integration handles the rest when you enable Agent mode in chat.

Yes, the server includes `lw.post_custom_query`. This tool lets Cursor send custom JSON payloads to override default search parameters during development.

Your search configurations and vector payloads are processed locally through secure stdio transport. No external servers cache your query profiles or index details, keeping your proprietary search logic safe.

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