How to Use the Lucidya MCP in Pydantic AI

Q: How do I register the Lucidya MCP Server within Pydantic AI?

You import MCPToolset from pydanticai.mcp and pass your Vinkius HTTP endpoint URL to the constructor. Register this toolset in the toolsets list when instantiating your Agent. The framework automatically imports all seven Lucidya tools and generates their runtime validation schemas.

Q: Can I use Pydantic AI to run type-safe sentiment analysis with Lucidya?

Yes, your agent calls analyzetextsentiment to evaluate social posts, and the framework validates the sentiment score against your defined float boundaries. This prevents your agent from executing downstream actions based on malformed or hallucinated sentiment metrics.

Build type-safe Arabic NLP agents with Pydantic AI and the Lucidya MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lucidya MCP to Pydantic AI

Create your Vinkius account to connect Lucidya 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 Lucidya with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Arabic dialect classification with Pydantic AI

`detect_arabic_dialect` identifies the regional dialect of a text, returning a structured response that Pydantic AI validates against your schema. The tool analyzes the linguistic patterns of the Arabic text and outputs the classification. If the API returns unexpected or malformed dialect codes, the framework raises a validation error immediately. This prevents your agent from passing corrupt dialect data to downstream translation or sentiment models, ensuring strict data integrity.

Enforce strict schemas on customer profile retrievals

`get_customer_profile` retrieves detailed records for a specific customer from your CDP. The tool returns fields like contact info, interaction history, and segment data, which are parsed directly into Pydantic models. By using this MCP Server, your Python code guarantees that every customer record matches your system's required types. If a profile is missing a critical field, the agent catches the error at runtime instead of failing silently inside your application logic.

Track customer service KPIs with type-safe analytics queries

`get_omniserve_analytics` queries your customer service KPIs to return structured performance data. The tool extracts metrics like response times and ticket volumes, mapping them directly to float and integer fields in your Python models. This type-safe parsing ensures that your analytics dashboards and automated reporting scripts never process malformed numbers. Pydantic AI handles the type coercion, so your agents can safely calculate averages and identify performance trends.

Setup guide

Set up Lucidya 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": {
        "lucidya-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Lucidya tools.",
)

result = await agent.run("List recent Lucidya 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 Lucidya. 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 Lucidya 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 Lucidya MCP in Pydantic AI

You import MCPToolset from pydantic_ai.mcp and pass your Vinkius HTTP endpoint URL to the constructor. Register this toolset in the toolsets list when instantiating your Agent. The framework automatically imports all seven Lucidya tools and generates their runtime validation schemas.

If the Lucidya server returns data that violates your defined schemas, Pydantic AI raises a ValidationError immediately. This ensures your application fails loudly and safely rather than processing corrupt customer profiles or incorrect sentiment scores.

Yes, your agent calls `analyze_text_sentiment` to evaluate social posts, and the framework validates the sentiment score against your defined float boundaries. This prevents your agent from executing downstream actions based on malformed or hallucinated sentiment metrics.

Yes, because Pydantic AI is model-agnostic, you can use the Lucidya tools with OpenAI, Anthropic, Gemini, or local models. The framework handles the schema translation, allowing you to switch LLMs without rewriting your `list_social_monitors` or customer lookup code.

Your customer profile and analytics data are protected during transport via SSL encryption managed by Vinkius. The MCP Server runs inside an ephemeral, zero-trust sandbox, ensuring that sensitive customer data retrieved by your agents is never cached 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