How to Use the Lyko MCP in Pydantic AI

Use Lyko with Pydantic AI for type-safe European transit planning that fails fast on bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lyko MCP to Pydantic AI

Create your Vinkius account to connect Lyko 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 Lyko with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate transit plans with Pydantic AI

The `plan_trip` tool returns complex itineraries that Pydantic AI validates against strict models at runtime. If the transit operator returns an unexpected field, the agent raises a validation error immediately. This prevents your agent from hallucinating data or proceeding with incomplete trip details. Every leg of the journey, including walking distances and transfer times, remains typed and verified throughout the planning process.

Get type-safe departure data in Pydantic AI

Invoke `get_departures` to pull upcoming schedule data into your agent. Pydantic AI ensures the response matches your schema, so the agent always knows exactly which line names and times are valid. This eliminates silent data corruption when transit operators change their API output formats. Your agent relies on the strictly defined model to interpret platform numbers and delay indicators correctly.

Query transit operators using Pydantic AI

Use `get_operators` to generate a list of available transit providers, filtered by country or mode. Pydantic AI validates the returned list against your defined structure, ensuring your agent only works with supported operators. This makes it easy to add new regions to your agent's capability list without changing your core logic. The agent simply validates the new operator data against the existing model.

Setup guide

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

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

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

Pydantic AI enforces strict schemas on all Lyko tool outputs. This prevents your agent from processing malformed transit data, which is common when dealing with fragmented European transit APIs.

The MCPToolset maps Lyko tools directly to your agent's logic. If the server returns a schema mismatch, Pydantic AI catches it during the response parsing phase, providing a clear error for debugging.

Yes. The MCP protocol uses a secure transport layer to fetch transit data. Pydantic AI ensures that only the data you explicitly model is extracted, minimizing the exposure of raw transit payloads.

Yes. The toolset is model-agnostic. Whether you use OpenAI or Anthropic, Pydantic AI validates the Lyko responses consistently, ensuring your transit agent stays reliable regardless of the underlying LLM.

The agent will throw a validation error. Because you've defined the structure of a valid trip, Pydantic AI rejects any response that doesn't match, stopping the agent from making errors based on corrupted data.

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