How to Use the EMT Madrid (Open Data) MCP in LlamaIndex

Q: How do I connect the EMT Madrid (Open Data) MCP Server to LlamaIndex?

Install the llama-index-tools-mcp package and initialize the basic client with your Vinkius endpoint. From there, convert the tools to a list and pass them to your FunctionAgent.

Q: Can LlamaIndex cache results from EMT Madrid (Open Data) tools?

Yes. You can store the output of tools like listbicimadstations in a local vector index to avoid hitting the API for every repetitive user query.

Q: How does this MCP Server help prevent hallucination in LlamaIndex?

By feeding raw JSON from getbusarrivals directly into the agent's context window, the model answers questions using live facts rather than training data.

Q: Where are my EMT Madrid (Open Data) login tokens stored in LlamaIndex?

Session tokens generated by the login tool are kept in memory during the runtime session. They are never committed to your vector store or persistent index.

Index real-time Madrid bus and bike data directly into your LlamaIndex vector store for grounded RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EMT Madrid (Open Data) MCP to LlamaIndex

Create your Vinkius account to connect EMT Madrid (Open Data) 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 EMT Madrid (Open Data) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live transit data into your knowledge base

LlamaIndex converts live API responses into searchable document nodes using this MCP Server. Your agent can query `list_bicimad_stations` to fetch bike availability and instantly index that status, making it searchable for future semantic queries. This approach prevents your agent from hallucinating transit options. It relies on actual, indexed data from `get_bus_arrivals` to answer user questions about current schedules and delays.

Build RAG applications with real-time context

Combining static transit documents with live data is simple. You can query a local PDF of Madrid's transit rules while pulling live route options via `plan_bus_route` to give users highly accurate travel advice. The framework blends these sources into a unified query engine. Your users get answers grounded in both official guidelines and real-time station statuses.

Filter active tools for specific transit queries

LlamaIndex allows you to restrict which MCP Server tools an agent can access during a session. You can limit a basic agent to only run `get_bus_arrivals` while reserving `plan_bus_route` for advanced routing workflows. This control reduces token usage and prevents the agent from running unnecessary API calls. It keeps your application fast and stays well within the free-tier API limits.

Setup guide

Set up EMT Madrid (Open Data) 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 EMT Madrid (Open Data) 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 EMT Madrid (Open Data) tools.",
)
response = await agent.run("List recent EMT Madrid (Open Data) 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 EMT Madrid. 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 EMT Madrid (Open Data) 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 EMT Madrid (Open Data) MCP in LlamaIndex

Install the `llama-index-tools-mcp` package and initialize the basic client with your Vinkius endpoint. From there, convert the tools to a list and pass them to your FunctionAgent.

Yes. You can store the output of tools like `list_bicimad_stations` in a local vector index to avoid hitting the API for every repetitive user query.

By feeding raw JSON from `get_bus_arrivals` directly into the agent's context window, the model answers questions using live facts rather than training data.

Absolutely. You can build a query engine that references your local documents alongside live results from `plan_bus_route` to answer complex commuting questions.

Session tokens generated by the `login` tool are kept in memory during the runtime session. They are never committed to your vector store or persistent index.

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