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

Q: How does Pydantic AI ensure query validation with Lucidworks Fusion (AI Search & Discovery)?

The agent uses lw.querysearch to fetch results, which are immediately validated against your Pydantic models. Any missing or malformed fields trigger a validation error, preventing silent failures.

Q: Can I retrieve filtered search results using this MCP Server?

Yes. The lw.queryfiltered tool allows your agent to extract specific properties while applying active account logic to filter the output.

Q: How do I track search relevance in Lucidworks Fusion (AI Search & Discovery) using Pydantic AI?

Your agent logs user telemetry using the lw.postsignal tool. This structured behavioral data is validated at runtime before being sent to update your ML profiles.

Q: What happens if a search collection schema changes?

When you run lw.listcollections, the agent retrieves the current list of collections. If a collection's schema changes, your Pydantic models will catch the discrepancy on the next search query.

Validate your search payloads at runtime using Pydantic AI with Lucidworks Fusion (AI Search & Discovery).

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run type-safe searches with Pydantic AI

`lw.query_search` executes semantic vector queries with strict runtime validation. The framework parses the returned search records against your Pydantic models, failing loudly if the schema deviates. You initialize the connection using the MCP toolset with your hosted server URL. This unified setup exposes all tools to your agent, ensuring that every query profile resolved via `lw.list_query_profiles` matches your code-level expectations.

Index documents with absolute type safety

`lw.index_documents` lets your agent write new records to your search collections. Because the framework validates payloads before dispatching them, you eliminate the risk of indexing corrupt or malformed search documents. You can verify active indexing pipelines using `lw.list_index_profiles`. The agent checks these profiles to ensure your raw data maps correctly to the target fields.

Post user signals using a type-safe MCP Server

`lw.post_signal` sends telemetry data to train your search models. The agent validates signal payloads at runtime, ensuring clickstream data matches the required schema before it hits the collection. If you need to run deep custom queries, `lw.post_custom_query` executes raw JSON logic safely. The agent checks active pipelines with `lw.list_jobs` to verify that custom queries don't disrupt background training tasks.

Setup guide

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

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

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

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Lucidworks Fusion (AI Search & Discovery) tools.",
)

result = await agent.run("List recent Lucidworks Fusion (AI Search & Discovery) transactions")
print(result.output)

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 Pydantic AI

The agent uses `lw.query_search` to fetch results, which are immediately validated against your Pydantic models. Any missing or malformed fields trigger a validation error, preventing silent failures.

Yes. The `lw.query_filtered` tool allows your agent to extract specific properties while applying active account logic to filter the output.

Your agent logs user telemetry using the `lw.post_signal` tool. This structured behavioral data is validated at runtime before being sent to update your ML profiles.

When you run `lw.list_collections`, the agent retrieves the current list of collections. If a collection's schema changes, your Pydantic models will catch the discrepancy on the next search query.

This MCP Server isolates your Solr credentials and API keys in a secure V8 sandbox. Only validated document payloads from `lw.index_documents` pass through, keeping your cluster access tokens hidden from the agent.

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