How to Use the Cabify MCP in LlamaIndex

Q: Can I index Cabify ride history into a LlamaIndex vector store?

Yes. You use getridehistory to pull past trip data, which LlamaIndex converts into document nodes for your vector database.

Q: How does LlamaIndex use Cabify price estimates for decision making?

The agent calls getpriceestimate to retrieve live fare options. It then compares these figures against your indexed corporate travel policies to approve or deny the ride request.

Q: Can I manage saved office locations using this tool?

Yes. You can query existing addresses with getsavedlocations or store new ones with addsavedlocation to keep your coordinate index updated.

Index Cabify travel data and coordinate history directly into LlamaIndex vector stores.

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 LlamaIndex

Create your Vinkius account to connect Cabify to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search over Cabify ride records

The Cabify MCP Server exposes `get_ride_history` to let your LlamaIndex pipeline extract and index corporate travel records. Your LlamaIndex agent queries past Cabify trip costs, driver details, and business expense categories, turning raw API outputs into searchable document nodes. By indexing this Cabify history, your LlamaIndex agent answers complex natural language queries about travel patterns without hitting the live API repeatedly. This setup grounds your LlamaIndex agent's answers in actual historical Cabify ride data rather than guesses.

Ground LlamaIndex queries in live Cabify rates

This MCP Server provides real-time ride data through `get_price_estimate` and `get_time_estimate` for your LlamaIndex query engines. Your LlamaIndex agent retrieves live Cabify rates and route durations, merging them with your internal travel policy documents. The LlamaIndex agent uses McpToolSpec to turn these Cabify endpoints into executable tools. It compares live Cabify estimates against your indexed corporate policies to determine if a requested trip complies with budget limits.

Locate saved destinations with LlamaIndex

The Cabify MCP Server lets your LlamaIndex agent query and search your corporate address book using `get_saved_locations` and `add_saved_location`. LlamaIndex indexes these coordinates and names, mapping them to semantic concepts like Cabify pickup zones. When a user asks to book a trip to a client site, the LlamaIndex agent searches your indexed locations, retrieves the exact Cabify coordinates, and prepares the ride request using `request_ride`.

Setup guide

Set up Cabify MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Cabify MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Cabify tools.",
)
response = await agent.run("List recent Cabify data")

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 LlamaIndex

Yes. You use `get_ride_history` to pull past trip data, which LlamaIndex converts into document nodes for your vector database.

The agent calls `get_price_estimate` to retrieve live fare options. It then compares these figures against your indexed corporate travel policies to approve or deny the ride request.

Install the package using pip install llama-index-tools-mcp. Use BasicMCPClient to connect, wrap it in McpToolSpec, and pass the tools to your FunctionAgent.

Yes. You can query existing addresses with `get_saved_locations` or store new ones with `add_saved_location` to keep your coordinate index updated.

Vinkius executes the server in an isolated V8 sandbox, ensuring your location coordinates and address names are never leaked. Your private geographic data is processed ephemerally and never stored on public servers.

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