How to Use the HERE (Location & Maps) MCP in OpenAI Agents SDK

Q: How do I use HERE (Location & Maps) with the OpenAI Agents SDK to find the best route?

Your agent calls the calculatev8route tool with a start and end point. The tool returns turn-by-turn directions. For multiple destinations, your agent should use calculateroutingmatrix first to determine the optimal order.

Q: What's the difference between calculatev8route and calculateroutingmatrix?

Use calculatev8route for a single trip from point A to B. Use calculateroutingmatrix to calculate travel times between many origins and many destinations, which is what you need for fleet logistics.

Q: Can my OpenAI agent get real-time traffic data with HERE (Location & Maps)?

Yes. The agent can call the gettrafficflow tool with a bounding box of coordinates. It gets back current traffic conditions, which it can use to make routing decisions.

Q: How does the OpenAI Agents SDK handle place searches with HERE (Location & Maps)?

An agent would first use forwardgeocode to get coordinates for an area, then pass those to discoverplaces with a category like 'coffee shop'. The SDK ensures the tools are called in the right sequence.

Build production-ready location agents with the OpenAI Agents SDK that understand maps, routes, and real-world traffic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HERE (Location & Maps) MCP to OpenAI Agents SDK

Create your Vinkius account to connect HERE (Location & Maps) to OpenAI Agents SDK 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 (Location & Maps) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Plan Multi-Stop Routes

Give your agents the ability to plan logistics. With this MCP Server, an agent can use `calculate_routing_matrix` to figure out the best sequence for a fleet of delivery drivers, then hand off individual jobs to other agents that use `calculate_v8_route` for turn-by-turn directions. This isn't just a single-shot tool. The OpenAI Agents SDK lets you chain these actions. A planning agent can monitor routes and, if `get_traffic_flow` shows a problem, it can recalculate and dispatch a new route to a driver's agent automatically. It's how you build systems that adapt.

React to Live Conditions

Your agent can now check the weather and traffic before making a decision. Use `get_weather_observation` to see if a hailstorm is on the route, or `get_traffic_flow` to check for a jam on the freeway. It's real-time data for smarter agent actions. Because you're using the OpenAI Agents SDK, every decision is traceable. You can look at the logs and see exactly why your agent chose to reroute a driver around a traffic incident. This makes debugging complex agent behavior way easier than trying to guess what it was thinking.

Actually Understand Addresses

An agent that can't handle addresses isn't very useful. Give it the tools to convert messy user input into actual coordinates with `forward_geocode`, or turn a dropped pin back into a street address with `reverse_geocode`. It’s the foundation for any location-aware task. Once your agent knows *where* it is, it can find out *what's* there. After getting coordinates, the agent can call `discover_places` to find nearby restaurants, parks, or charging stations. The SDK's built-in guardrails help prevent your agent from spamming the API with malformed requests.

Setup guide

Set up HERE (Location & Maps) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all HERE (Location & Maps) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives HERE (Location & Maps) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate HERE (Location & Maps) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="HERE (Location & Maps) Agent",
            instructions="You have access to HERE (Location & Maps) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Technologies. 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 (Location & Maps) 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 (Location & Maps) MCP in OpenAI Agents SDK

Your agent calls the `calculate_v8_route` tool with a start and end point. The tool returns turn-by-turn directions. For multiple destinations, your agent should use `calculate_routing_matrix` first to determine the optimal order.

Use `calculate_v8_route` for a single trip from point A to B. Use `calculate_routing_matrix` to calculate travel times between many origins and many destinations, which is what you need for fleet logistics.

Yes. The agent can call the `get_traffic_flow` tool with a bounding box of coordinates. It gets back current traffic conditions, which it can use to make routing decisions.

An agent would first use `forward_geocode` to get coordinates for an area, then pass those to `discover_places` with a category like 'coffee shop'. The SDK ensures the tools are called in the right sequence.

The MCP server only processes the data needed for the task, like address strings or GPS coordinates. Vinkius runs the server in an ephemeral sandbox, so this data isn't stored after your request. OpenAI's platform handles agent-level data according to their policies.

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