How to Use the HERE Mobility MCP in LlamaIndex

Q: How can I use LlamaIndex and HERE Mobility to remember previous trip searches?

LlamaIndex can index the output from tools like discovertrips and searchmultimodaltrips. This builds a searchable history, allowing your agent to answer questions about past routes without re-running the queries against the live API.

Q: How do I prevent my LlamaIndex agent from making up station names when using HERE Mobility?

You ground it in facts by indexing the output of getstations or getstationsbyname. When the agent needs to answer a question, it queries this index of real station data first, which prevents it from hallucinating names or locations.

Q: Is it possible to build a semantic search over all bus routes in a city?

Definitely. You would programmatically call discovertrips for various key locations and index the results into your vector store. Your LlamaIndex agent could then answer natural language questions like 'Show me routes that go from downtown to the airport.'

Build knowledge-rich transit apps with LlamaIndex. Index HERE Mobility data to answer questions about routes and station history.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HERE Mobility MCP to LlamaIndex

Create your Vinkius account to connect HERE Mobility 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 HERE Mobility with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Transit Data for Smarter Queries

LlamaIndex turns API calls into a knowledge base. Run `get_stations` for a city, and the results—station names, lines, coordinates—are indexed into a vector store. Now your agent isn't just calling an API; it's querying a local, semantic cache of transit data. This means your agent can answer follow-up questions without hitting the API again. Ask 'Which of those stations are on the Blue Line?' and LlamaIndex finds the answer from the data it just indexed. It's faster and saves on API calls.

Augment Trip Planning with LlamaIndex RAG

Combine live data with stored knowledge. Your agent can fetch a new route using `discover_trips`. LlamaIndex then uses that route info as context to query your other data sources, like documents about local events or business reviews near the destination station. This creates a much richer response. Instead of just a route, the user gets the route *plus* relevant information about what's at their destination. The `get_station_details` tool provides station-specific context that gets indexed, too.

Ground Agents in Real-World Station Data

Stop agent hallucinations about transit. By calling `get_nearby_stations` and `get_schedule` and indexing the results, you create a factual foundation for your agent. When a user asks about the next train, the answer is pulled from the actual schedule data you just indexed from the MCP Server. You can even pre-populate the index by running `get_stations_by_name` for all major hubs in a city. This ensures your agent starts with a solid, fact-based understanding of the local transit network.

Setup guide

Set up HERE Mobility 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 HERE Mobility 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 HERE Mobility tools.",
)
response = await agent.run("List recent HERE Mobility 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 HERE Mobility. 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 HERE Mobility 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 HERE Mobility MCP in LlamaIndex

LlamaIndex can index the output from tools like `discover_trips` and `search_multimodal_trips`. This builds a searchable history, allowing your agent to answer questions about past routes without re-running the queries against the live API.

Yes, that's the point of RAG with LlamaIndex. You can index station information from `get_station_details` alongside your own PDFs or text files about those locations to provide richer, more contextual answers.

You ground it in facts by indexing the output of `get_stations` or `get_stations_by_name`. When the agent needs to answer a question, it queries this index of real station data first, which prevents it from hallucinating names or locations.

Definitely. You would programmatically call `discover_trips` for various key locations and index the results into your vector store. Your LlamaIndex agent could then answer natural language questions like 'Show me routes that go from downtown to the airport.'

The MCP server itself only handles the transit data you query, like station IDs and coordinates. The indexed data lives in your LlamaIndex application's vector store. Vinkius ensures the API transaction is secure, running in a sandboxed environment that doesn't persist your query history.

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