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

Q: Can LangChain agents automatically trigger ML training runs via this MCP Server?

Yes. Your agent can check active pipelines using lw.listjobs and make decisions on whether to initiate new indexing runs based on the current status.

Q: How does the Lucidworks Fusion (AI Search & Discovery) MCP Server handle query profiles with LangChain?

The server exposes lw.listqueryprofiles directly to your agent. This allows the LangChain runner to inspect available search endpoints and choose the most relevant profile before executing a query.

Get raw search results and push user click telemetry directly inside your LangChain reasoning loops.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route search queries dynamically with LangChain

The `lw.query_search` tool is part of this MCP Server that lets your agent query your Fusion index to pull relevant documents based on user intent. We expose this directly to your LangChain agent so it can decide which query profile to hit based on the incoming message. By combining this with `lw.list_query_profiles`, your pipeline evaluates the active routes before firing the query. You get raw search results injected directly into your chain's context window.

Feed user clicks back to Fusion from your agent

The `lw.post_signal` tool sends telemetry data like click events and search interactions back to Lucidworks to train your relevance models. LangChain chains can trigger this tool automatically right after a user confirms they found what they needed. This creates a closed loop where your app gets smarter with every interaction. You don't have to write custom tracking code because the agent handles the signal posting as a post-execution step.

Track indexing jobs inside your LangSmith runs

The `lw.index_documents` tool pushes raw data into your search collections for immediate indexing. When your LangChain agent processes new files, it feeds them to this tool to keep the search index fresh. You can also use `lw.list_jobs` to monitor the training runs or ingestion progress. This MCP Server handles the connection details so every tool execution shows up in your LangSmith dashboard, giving you clear visibility into latency and token usage.

Setup guide

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

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Lucidworks Fusion (AI Search & Discovery) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "lucidworks-fusion-ai-search-discovery-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Lucidworks Fusion (AI Search & Discovery) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You can chain your search queries together by feeding the output of one tool into another. For example, have your agent run `lw.query_search` to find initial documents, analyze the results, and then use `lw.query_filtered` to drill down into specific metadata fields.

Yes. Your agent can check active pipelines using `lw.list_jobs` and make decisions on whether to initiate new indexing runs based on the current status.

The server exposes `lw.list_query_profiles` directly to your agent. This allows the LangChain runner to inspect available search endpoints and choose the most relevant profile before executing a query.

Because every tool call runs through the standard protocol, you can use LangSmith tracing to monitor the exact execution time, inputs, and outputs of your search queries.

Your search queries and indexed documents stay within your secure environment. This integration uses local V8 isolates on Vinkius, meaning your raw database credentials and search parameters are never logged or exposed to third parties.

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