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

Q: Can I use Claude Desktop to monitor ML training jobs in Lucidworks Fusion (AI Search & Discovery)?

Yes, you can track them directly in your chat. Claude uses lw.listjobs to check the current status of your Solr and Fusion machine learning pipelines.

Q: Can I test raw Solr queries with this setup?

Yes, you can. The lw.postcustomquery tool lets your agent send custom JSON payloads to override default vector parameters, letting you test relevance directly.

Get live search relevance and run raw Solr vector queries right inside Claude Desktop.

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 Claude Desktop

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run deep vector queries inside Claude Desktop

The `lw.query_search` tool lets your agent hit your Fusion endpoints and pull back raw matching records instantly without writing complex API requests by hand. It handles the heavy lifting of sorting through your collection structures. If you need to tweak the raw query parameters directly, the `lw.post_custom_query` tool lets your agent send custom JSON payloads to override Solr vectors. This means you can test search relevance configurations without opening a separate terminal window.

Track user signals to train ML models

Logging search clicks and document views is handled by the `lw.post_signal` tool to feed your recommendation pipelines directly from your chat window using this MCP Server. Your agent can send this telemetry data instantly to update user behavior profiles. You can keep tabs on how those training pipelines are running using `lw.list_jobs`. Checking the status of active ML training runs ensures your new signal data is reflected in search results.

Manage active index profiles on the fly

Your agent invokes `lw.list_collections` to pull back active collections and their rules in real time without digging through the admin console. Having this structural view lets you inspect your schemas in seconds. When you need to verify how documents are parsed, `lw.list_index_profiles` shows you the exact pipelines processing your incoming data. Running `lw.index_documents` lets you push fresh test payloads directly into the index for immediate verification.

Setup guide

Set up Lucidworks Fusion (AI Search & Discovery) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Lucidworks Fusion (AI Search & Discovery) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Lucidworks Fusion (AI Search & Discovery) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under lucidworks-fusion-ai-search-discovery-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 Claude Desktop

Just ask Claude to search your collections. Under the hood, this MCP Server fires off `lw.query_search` to hit your configured Fusion query profile and pull back ranked results.

Yes, you can track them directly in your chat. Claude uses `lw.list_jobs` to check the current status of your Solr and Fusion machine learning pipelines.

You have two options depending on your workflow. Add the server configuration to your local config file, or connect it via the Integrations tab on the web version of Claude, which lets you plug a remote MCP server URL directly.

Yes, you can. The `lw.post_custom_query` tool lets your agent send custom JSON payloads to override default vector parameters, letting you test relevance directly.

All search queries and document payloads run through a zero-trust, ephemeral V8 isolate sandbox. Your credentials and raw Solr payloads are never stored, meaning your search index data stays completely within your network.

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