Lyko MCP Server for LlamaIndex 12 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Lyko as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to Lyko. "
"You have 12 tools available."
),
)
response = await agent.run(
"What tools are available in Lyko?"
)
print(response)
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 Lyko MCP Server
Connect your Lyko Transit API mobility platform to any AI agent and take full control of European public transit planning, real-time departure monitoring, and multimodal journey optimization through natural conversation.
LlamaIndex agents combine Lyko tool responses with indexed documents for comprehensive, grounded answers. Connect 12 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
What you can do
- Trip Planning — Plan door-to-door intermodal journeys combining buses, trains, subways, trams, ferries, bike-sharing, and walking
- Real-Time Departures — Check upcoming departures at any transit stop with ETAs, platforms, and delay indicators
- Arrival Tracking — Monitor incoming services for passenger pickup and connection coordination
- Stop Discovery — Search transit stops by name, address, or landmark across 300+ European operators
- Nearby Stops — Find all transit stops near any geographic location with distance calculations
- Stop Details — Get comprehensive stop information including served lines, accessibility, and amenities
- Line Information — Research transit lines with operator details, service hours, and route characteristics
- Line Routes — View complete stop sequences and route patterns for any transit line
- Operator Directory — Browse 300+ transit operators across Europe with coverage areas and service modes
- Network Status — Check service disruptions, planned works, strikes, and delay alerts for any operator
- GTFS Feeds — Access raw GTFS transit data for offline analysis and academic research
- Trip Booking — Book train tickets, bus passes, bike rentals, and other mobility services through Lyko Book
The Lyko MCP Server exposes 12 tools through the Vinkius. Connect it to LlamaIndex 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 Lyko to LlamaIndex via MCP
Follow these steps to integrate the Lyko MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from Lyko
Why Use LlamaIndex with the Lyko MCP Server
LlamaIndex provides unique advantages when paired with Lyko through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine Lyko tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain Lyko tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query Lyko, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what Lyko tools were called, what data was returned, and how it influenced the final answer
Lyko + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the Lyko MCP Server delivers measurable value.
Hybrid search: combine Lyko real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query Lyko to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Lyko for fresh data
Analytical workflows: chain Lyko queries with LlamaIndex's data connectors to build multi-source analytical reports
Lyko MCP Tools for LlamaIndex (12)
These 12 tools become available when you connect Lyko to LlamaIndex via MCP:
book_trip
Supports booking train tickets, bus tickets, bike-sharing rentals, car-sharing reservations, and other mobility services available through the Lyko Book platform. Returns booking confirmation, payment details, ticket information, QR codes for validation, and cancellation policies. Availability and booking capabilities vary by operator and service type. Essential for Mobility-as-a-Service integration, ticket purchasing, service reservations, and end-to-end journey planning with booking. AI agents should use this when users ask "book this train ticket", "reserve a bike for this trip", or want to complete a mobility service reservation after planning a route. Book a transit trip or mobility service through Lyko Book
get_arrivals
Returns list of arriving services with line names and numbers, origins, scheduled and real-time arrival times (ETA), platform or bay information, delay indicators, and operator details. Essential for passenger pickup coordination, arrival monitoring, transit hub management, and real-time arrival boards. AI agents use this when users ask "when does the next train arrive at X", "show incoming services at this station", or need to track arriving services for passenger coordination. Get upcoming arrivals at a specific transit stop
get_departures
Returns list of departing services with line names and numbers, destinations, scheduled and real-time departure times (ETD), platform or bay information, delay indicators, and operator details. Supports buses, trains, trams, subways, and ferries across European transit networks. Essential for passenger information displays, departure boards, travel apps, and real-time transit monitoring. AI agents should reference this when users ask "when is the next bus from stop X", "show departures from this station", or need to monitor upcoming services at a known transit stop. Get next departures from a specific transit stop
get_line_info
Returns line name, number, type (bus, train, tram, subway, ferry), operator, color code, route description, service hours, frequency, and accessibility information. Essential for line identification, transit network exploration, service information queries, and route planning context. AI agents should reference this when users ask "tell me about line M1", "what operator runs bus line 42", or need line metadata to understand transit service characteristics. Get information about a specific transit line
get_line_routes
Returns route variants (e.g., direction A and B), complete stop sequences with order, scheduled frequencies, first and last service times, and any service variations (express vs. local, peak vs. off-peak). Essential for complete line visualization, stop sequence analysis, transit mapping, and understanding service patterns. AI agents use this when users ask "show me all stops on line X", "what is the full route of bus 42", or need to understand complete service patterns for a transit line. Get all routes and stops for a specific transit line
get_nearby_stops
Returns nearby stops with distances from the coordinate, stop names, locations, served lines, operators, and stop types, sorted by proximity. Essential for location-based transit discovery, passenger navigation, "stops near me" features, and geographic transit analysis. AI agents use this when users ask "what stops are near my current location", "find transit stops within 500m of these coordinates", or need to discover accessible transit options from a specific point. Find transit stops near a geographic location
get_network_status
Returns active service disruptions, planned works, line closures, delay information, weather impacts, strike notifications, and alternative service recommendations. Essential for real-time service monitoring, disruption awareness, passenger communication, and travel planning during service changes. AI agents should reference this when users ask "are there any disruptions on SNCF trains", "is the Berlin U-Bahn running normally", or need to check service reliability before planning trips. Get current network status and service alerts for a transit operator
get_operators
Returns operator names, IDs, countries, coverage areas, transport modes operated (bus, train, tram, subway, ferry), contact information, and service status. Covers 300+ operators across Europe including SNCF (France), DB (Germany), NS (Netherlands), RENFE (Spain), Trenitalia (Italy), and many regional and local operators. Essential for operator research, transit network scoping, country-specific transit analysis, and understanding service coverage. AI agents should use this when users ask "what transit operators are available in France", "list all train operators in Germany", or need to identify operators for a specific country or region. List public transit operators available in a country or region
get_stop_info
Returns stop name, location (latitude, longitude, address), served lines and routes, stop type (bus stop, train station, tram stop, subway station, ferry terminal), operator information, accessibility features (wheelchair access, elevators), and available amenities. Essential for stop identification, accessibility planning, transit network analysis, and passenger information. AI agents should use this when users ask "tell me about this stop", "what lines serve stop X", or need detailed stop metadata to contextualize transit queries. Get detailed information about a specific transit stop
get_transit_feed
Returns feed metadata, last update timestamp, included operators, coverage area, data freshness indicators, and download or access URLs. GTFS feeds contain static schedule data, route definitions, stop locations, fare information, and service calendars. Essential for transit data analysis, offline planning applications, academic research, and transit network visualization. AI agents use this when users need access to raw GTFS data, want to analyze transit schedules offline, or require complete network definitions for planning applications. Access GTFS transit feed data for a specific operator or region
plan_trip
Supports multiple transport modes including buses, trains, subways, trams, ferries, bike-sharing, car-sharing, and walking combinations. Returns complete itinerary with departure and arrival times, duration, number of transfers, legs with mode details (line name, operator, vehicle type), intermediate stops, walking distances, fares if available, and real-time delay information. Essential for travel planning, multimodal journey optimization, passenger information systems, and Mobility-as-a-Service (MaaS) applications. AI agents should use this when users ask "how do I get from X to Y by public transport", "plan a trip from Paris Gare du Nord to Versailles", or need intermodal route options with timing and transfer details. Plan an intermodal trip between two locations using public transit
search_stops
Returns matching stops with stop IDs, names, locations (latitude, longitude), served lines, operators, and stop types. Essential for stop discovery, journey planning interfaces, transit stop identification, and building location-based transit features. AI agents should use this when users ask "find the bus stop near Champs-Elysees", "search for stops called X", or need to identify stop IDs for use in departure/arrival queries. Search for transit stops by name or location
Example Prompts for Lyko in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with Lyko immediately.
"Plan a trip from Paris Gare du Nord to the Palace of Versailles using public transit."
"Show me all departures from Berlin Alexanderplatz station in the next 30 minutes."
"What transit operators are available in the Netherlands, and is NS (Dutch Railways) running normally today?"
Troubleshooting Lyko MCP Server with LlamaIndex
Common issues when connecting Lyko to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpLyko + LlamaIndex FAQ
Common questions about integrating Lyko MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Connect Lyko 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 Lyko to LlamaIndex
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.