How to Use the Cabify MCP in Pydantic AI

Q: How does Pydantic AI prevent errors when calling the Cabify ride booking tool?

The framework validates the arguments for requestride against strict Pydantic models before execution. If the coordinates or product IDs are invalid, the agent fails loudly instead of sending bad data to Cabify.

Q: Can I use Pydantic AI to parse Cabify ride history into custom financial models?

Yes. You can feed the output of getridehistory directly into your custom Pydantic schemas. This ensures every expense category, date, and cost is validated before entering your database.

Q: How do I connect Pydantic AI to the Cabify MCP Server?

Use the unified MCPToolset with your server's HTTP endpoint and pass it to the Agent constructor. This replaces the deprecated MCPServerHTTP class for a more stable connection.

Q: What happens if a Cabify estimation tool returns an unexpected currency?

The getpriceestimate tool returns the local currency of the region. Pydantic AI will parse this string or numeric value into your validated model, allowing your code to handle currency conversions safely.

Build type-safe Cabify travel agents with Pydantic AI to guarantee runtime validation on every MCP ride booking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cabify MCP to Pydantic AI

Create your Vinkius account to connect Cabify 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 Cabify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe ride requests using Pydantic AI

Stop worrying about malformed coordinates crashing your corporate travel scripts. Pydantic AI validates the outputs of `get_price_estimate` and `request_ride` at runtime, ensuring that your agent only processes valid latitude and longitude data. If the Cabify API returns an unexpected format, the framework raises a validation error immediately. This prevents your agent from booking rides with corrupt location IDs or incorrect service tiers, protecting your travel budget from silent failures.

Strict validation for corporate travel audits

Auditing business expenses requires absolute precision. When your agent calls `get_ride_history`, Pydantic AI parses the ride dates, costs, and business expense categories directly into typed Python schemas, rejecting any incomplete records. This strict schema enforcement makes it easy to integrate travel logs with your internal accounting systems. If a trip's cost data is missing or corrupted, the validation layer blocks the entry, ensuring your financial database remains clean.

Reliable MCP tool mapping for multi-model setups

No matter which model provider you use, the unified `MCPToolset` ensures consistent tool behavior across your entire system. Your agent can query `get_available_products` and `get_time_estimate` using the exact same type constraints on every run. By running the server externally and connecting via Streamable HTTP, you decouple your agent logic from the API transport. This clean separation keeps your travel dispatch code modular, testable, and highly resilient to API changes.

Setup guide

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

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

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

The framework validates the arguments for `request_ride` against strict Pydantic models before execution. If the coordinates or product IDs are invalid, the agent fails loudly instead of sending bad data to Cabify.

Yes. You can feed the output of `get_ride_history` directly into your custom Pydantic schemas. This ensures every expense category, date, and cost is validated before entering your database.

Use the unified `MCPToolset` with your server's HTTP endpoint and pass it to the `Agent` constructor. This replaces the deprecated `MCPServerHTTP` class for a more stable connection.

The `get_price_estimate` tool returns the local currency of the region. Pydantic AI will parse this string or numeric value into your validated model, allowing your code to handle currency conversions safely.

All ride details and pricing estimates are processed in an isolated, ephemeral runtime environment. No transit data is written to disk, and your API credentials are never exposed, keeping your corporate travel movements completely private.

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