Cabify MCP Server for AutoGen 9 tools — connect in under 2 minutes
Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add Cabify as an MCP tool provider through Vinkius and every agent in the group can access live data and take action.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with McpWorkbench(
server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
transport="streamable_http",
) as workbench:
tools = await workbench.list_tools()
agent = AssistantAgent(
name="cabify_agent",
tools=tools,
system_message=(
"You help users with Cabify. "
"9 tools available."
),
)
print(f"Agent ready with {len(tools)} tools")
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Cabify MCP Server
What you can do
Connect AI agents to the Cabify Business platform for enterprise mobility management:
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Cabify tools. Connect 9 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
- Get price estimates across all Cabify tiers (Lite, Executive, Taxi)
- Compare trip durations with real-time traffic data
- Request rides directly with pickup and dropoff coordinates
- Track active rides with driver info, vehicle details, and live ETA
- Cancel rides when plans change
- View complete ride history with business expense tracking
- Manage saved locations for frequent business destinations
- Check available service tiers at any location in Spain and LATAM
The Cabify MCP Server exposes 9 tools through the Vinkius. Connect it to AutoGen in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Cabify to AutoGen via MCP
Follow these steps to integrate the Cabify MCP Server with AutoGen.
Install AutoGen
Run pip install "autogen-ext[mcp]"
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Integrate into workflow
Use the agent in your AutoGen multi-agent orchestration
Explore tools
The workbench discovers 9 tools from Cabify automatically
Why Use AutoGen with the Cabify MCP Server
AutoGen provides unique advantages when paired with Cabify through the Model Context Protocol.
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Cabify tools to solve complex tasks
Role-based architecture lets you assign Cabify tool access to specific agents. a data analyst queries while a reviewer validates
Human-in-the-loop support: agents can pause for human approval before executing sensitive Cabify tool calls
Code execution sandbox: AutoGen agents can write and run code that processes Cabify tool responses in an isolated environment
Cabify + AutoGen Use Cases
Practical scenarios where AutoGen combined with the Cabify MCP Server delivers measurable value.
Collaborative analysis: one agent queries Cabify while another validates results and a third generates the final report
Automated review pipelines: a researcher agent fetches data from Cabify, a critic agent evaluates quality, and a writer produces the output
Interactive planning: agents negotiate task allocation using Cabify data to make informed decisions about resource distribution
Code generation with live data: an AutoGen coder agent writes scripts that process Cabify responses in a sandboxed execution environment
Cabify MCP Tools for AutoGen (9)
These 9 tools become available when you connect Cabify to AutoGen via MCP:
add_saved_location
Common use cases: save office addresses, frequent client locations, hotels, airports. Returns the saved location details including the new location ID. Use this to build a library of frequently used destinations for faster ride booking. Save a new location for the Cabify account
cancel_ride
Cancellation policies vary based on ride status - cancellations after driver assignment may incur fees depending on Cabify Empresas policy. Use this to cancel rides that were booked by mistake or are no longer needed. Cancel an existing Cabify ride request
get_available_products
Returns product IDs, names, descriptions, capacity, and features. Use this to see which service options are available before requesting estimates or booking rides. Get available Cabify service tiers at a location
get_price_estimate
Prices are in local currency (EUR for Spain, local currency for LATAM). Use this to compare costs across different Cabify service tiers before booking. Get price estimate for a Cabify ride between two locations
get_ride_details
Use this to track your active ride or review past trip details. Get details of a specific Cabify ride
get_ride_history
Returns ride date, status, origin/destination, product type, driver, cost, and business expense category. Use this to review past rides, calculate business expenses, or find previous trip details. Get ride history for the Cabify Business account
get_saved_locations
Returns location IDs, names, addresses, and coordinates. Use this to quickly reference saved locations for ride requests without typing full addresses. Common for frequent business destinations. Get saved locations for the Cabify account
get_time_estimate
Accounts for current traffic conditions and typical route times. Use this to plan schedules and compare route efficiency across different pickup/dropoff points. Get estimated trip duration for a Cabify ride
request_ride
Requires origin and destination coordinates. Optionally specify product ID (from get_available_products), pickup address, and dropoff address for clarity. Returns the ride ID, driver assignment status, and estimated pickup time. Use this to book a ride after confirming price and availability. Request a new Cabify ride
Example Prompts for Cabify in AutoGen
Ready-to-use prompts you can give your AutoGen agent to start working with Cabify immediately.
"Get me a price estimate from Madrid Airport to our office in Gran Vía for a Cabify Executive"
"Book a Cabify from the hotel to the conference center for 9am tomorrow"
"Show me all Cabify rides from last month with total business expenses"
Troubleshooting Cabify MCP Server with AutoGen
Common issues when connecting Cabify to AutoGen through the Vinkius, and how to resolve them.
McpWorkbench not found
pip install "autogen-ext[mcp]"Cabify + AutoGen FAQ
Common questions about integrating Cabify MCP Server with AutoGen.
How does AutoGen connect to MCP servers?
Can different agents have different MCP tool access?
Does AutoGen support human approval for tool calls?
Connect Cabify with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Cabify to AutoGen
Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.