Can my agent calculate reachability zones using time limits?

Yes. Use the 'calculate_reachability_polygon' tool. Provide a starting point and a time limit in seconds. The agent will retrieve the isochrone polygon defining exactly what area is reachable within that duration natively.

How do I optimize a multi-stop delivery route via chat?

Use the 'submit_vrp_optimizer' tool. Provide a JSON payload defining your vehicles and service stops. The agent will trigger the VRP solver to calculate the most efficient sequence, accounting for time windows and capacities synchronously.

Can I perform reverse geocoding to find a street name through the agent?

Absolutely. Use the 'reverse_geocode' tool. Provide the latitude and longitude. Your agent will analyze the global OSM bounds to match the coordinates exactly against the nearest physical street address flawlessy.

GraphHopper MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: GraphHopper
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect GraphHopper through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="GraphHopper Assistant",
            instructions=(
                "You help users interact with GraphHopper. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from GraphHopper"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 GraphHopper MCP Server

Connect your GraphHopper account to any AI agent and take full control of your geospatial routing, geocoding, and fleet optimization through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from GraphHopper through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries GraphHopper, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Route Orchestration — Calculate optimal routes between multiple GPS stops, identifying precise asynchronous directions and time calculations bypassing URL length limits natively
Geocoding discovery — Extract explicitly attached REST arrays targeting /geocode to translate human-readable addresses into precise LatLon coordinates for spatial analysis
Reverse Geocoding — Perform structural extraction of properties matching GPS pins exactly against named physical streets to verify localized entity bounds flawlessly
Routing Matrix Calculation — Generate N x M arrays of travel times and distances to analyze complex grid logistics and distance tables between multiple points synchronously
Isochrone Reachability — Identify precisely the boundary reachable in a specific time limit from a starting point, defining reachability polygons for site selection or delivery zones
VRP Optimization — Command explicit JSON targets firing Traveling Salesman configs for multiple vehicles, checking time windows and capacity constraints to solve complex logistics synchronously
Map Matching Auditing — Validate API logic correcting imprecise GPS jumps by snapping raw GPX tracks perfectly onto street vectors limitlessly

The GraphHopper MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 GraphHopper to OpenAI Agents SDK via MCP

Follow these steps to integrate the GraphHopper MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from GraphHopper

Why Use OpenAI Agents SDK with the GraphHopper MCP Server

OpenAI Agents SDK provides unique advantages when paired with GraphHopper through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

GraphHopper + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the GraphHopper MCP Server delivers measurable value.

Automated workflows: build agents that query GraphHopper, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries GraphHopper, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through GraphHopper tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query GraphHopper to resolve tickets, look up records, and update statuses without human intervention

GraphHopper MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect GraphHopper to OpenAI Agents SDK via MCP:

calculate_distance_isochrone

Provision a highly-available JSON Payload generating physical borders

calculate_heavy_route

Identify precise active arrays spanning native multi-stop geometries

calculate_reachability_polygon

Enumerate explicitly attached structured rules exporting active Reachability

calculate_routing_matrix

Inspect deep internal arrays mitigating specific Math tables

calculate_url_route

Retrieve explicit Cloud logging tracing explicit lightweight Directions

poll_vrp_solution

Retrieve the exact structural matching verifying Delivery alternatives

reverse_geocode

Perform structural extraction of properties driving active OSM bindings

search_geocode

Identify bounded routing spaces inside the Headless GraphHopper Engine

snap_gpx_to_road

Irreversibly vaporize explicit validations extracting GPX logic natively

submit_vrp_optimizer

Dispatch an automated validation check routing explicit jsprit solves

Example Prompts for GraphHopper in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with GraphHopper immediately.

"Calculate a car route between '40.71, -74.00' and '40.75, -73.98'"

"Show me the 10-minute reachability zone from central Berlin"

"Reverse geocode these coordinates: '48.85, 2.35'"

Troubleshooting GraphHopper MCP Server with OpenAI Agents SDK

Common issues when connecting GraphHopper to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

GraphHopper + OpenAI Agents SDK FAQ

Common questions about integrating GraphHopper MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.