How to Use the Cabify MCP in OpenAI Agents SDK

Q: How do I handle Cabify ride cancellations safely inside my OpenAI Agents SDK pipeline?

Use the cancelride tool within an agent that has strict guardrails enabled. The SDK will trace the cancellation request, allowing you to check if any Cabify Empresas fees apply before confirming the action.

Q: How does the OpenAI Agents SDK discover Cabify MCP tools?

The SDK uses MCPServerStreamableHttp to auto-discover all 9 tools, including getridehistory and addsavedlocation. You just pass the server instance inside the mcpservers list when initializing your agent.

Q: How does caching improve travel booking performance?

Setting cacheToolsList=True stops the agent from querying the server schema repeatedly. When pulling frequent routes using getsavedlocations or checking travel times with gettimeestimate, the agent responds much faster.

Run safe, multi-agent Cabify dispatch systems in production using the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Cabify to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded booking with OpenAI Agents SDK

Your OpenAI agents can now book corporate travel safely by combining `request_ride` and `get_price_estimate`. Because this SDK supports strict MCP guardrail validation, you can enforce spending limits before the agent ever sends a ride request to the Cabify platform. While the agent checks `get_available_products` to find the cheapest corporate tier, the OpenAI tracing dashboard records every decision step. If a ride exceeds your budget, the guardrail stops the transaction, preventing unauthorized corporate spending on high-end tiers.

Multi-agent coordination for travel expenses

One agent handles logistics while another reconciles financial data. The dispatch agent triggers `get_ride_history` to pull past trip invoices, then hands off the data to your accounting agent to match Cabify expense categories with internal ledgers. Using the `MCPServerStreamableHttp` connection, both agents share the same tool definitions without redundant API calls. If a ride needs to be canceled due to scheduling shifts, the system triggers `cancel_ride` and immediately notifies the accounting agent to expect a cancellation fee.

Fast location mapping using cached MCP tools

Speed up agent response times during peak hours by setting `cacheToolsList=True` in your OpenAI server configuration. Your agent can instantly fetch coordinates with `get_saved_locations` and match them to destination profiles without reloading the schema on every run. When a user requests a ride to a common office, the cached MCP tools allow the agent to run `add_saved_location` or estimate transit times via `get_time_estimate` in milliseconds. This setup keeps your production travel pipeline fast, responsive, and light on system resources.

Setup guide

Set up Cabify MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Cabify tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Cabify tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cabify tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Cabify Agent",
            instructions="You have access to Cabify tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the `cancel_ride` tool within an agent that has strict guardrails enabled. The SDK will trace the cancellation request, allowing you to check if any Cabify Empresas fees apply before confirming the action.

Yes. You can configure a validator in your SDK agent that checks the output of `get_price_estimate` and `get_available_products`. If the estimated cost exceeds your company's threshold, the agent can abort before calling `request_ride`.

The SDK uses `MCPServerStreamableHttp` to auto-discover all 9 tools, including `get_ride_history` and `add_saved_location`. You just pass the server instance inside the `mcp_servers` list when initializing your agent.

Setting `cacheToolsList=True` stops the agent from querying the server schema repeatedly. When pulling frequent routes using `get_saved_locations` or checking travel times with `get_time_estimate`, the agent responds much faster.

The server processes your corporate travel history and expense categories inside a secure, ephemeral V8 isolate. No trip logs, coordinates, or cost data are ever stored on Vinkius servers, ensuring complete isolation of your corporate travel records.

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