How to Use the GraphHopper MCP in LlamaIndex

Q: How do I index GraphHopper route geometries inside LlamaIndex?

You capture the coordinates from calculateurlroute and insert them as node metadata. LlamaIndex then indexes these coordinates, making your routing URLs searchable via vector queries.

Q: Can a LlamaIndex agent solve vehicle routing problems using GraphHopper?

Yes, the agent triggers submitvrpoptimizer and indexes the final dispatch plan. This lets you run semantic queries against your optimized fleet schedules using this MCP Server.

Q: How does LlamaIndex handle the JSON payloads from GraphHopper matrix calculations?

The agent processes the raw output from calculateroutingmatrix and splits it into searchable document chunks. This makes your distance tables queryable by natural language.

Index live GraphHopper routing and geocoding outputs directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GraphHopper MCP to LlamaIndex

Create your Vinkius account to connect GraphHopper 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 GraphHopper with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

RAG-Augmented Spatial Querying

LlamaIndex agents index the geographic data returned by `reverse_geocode` to ground your search queries in real-world location properties. This allows your RAG application to search past geocoding results using semantic vector queries. Instead of querying the live API for repetitive address lookups, your agent checks the local vector index first. Local caching of these coordinates saves API credits during repetitive runs.

LlamaIndex Reachability Polygons for Localized Search

This MCP Server generates spatial boundaries using `calculate_reachability_polygon` that LlamaIndex turns into searchable metadata filters. Your agent can query documents that fall strictly within specific drive-time polygons. The agent maps these complex geometries into your vector store index. This means your location-based document retrieval is based on actual road networks rather than straight-line approximations.

Heavy Route Telemetry Indexing

Your LlamaIndex pipeline processes truck-specific paths with `calculate_heavy_route` and stores the resulting geometries for future reference. The agent can then answer driver queries by retrieving these indexed route profiles. Storing these specific geometry arrays lets you build a historical database of safe truck routes. Your agent queries this MCP index to find patterns in past routing decisions.

Setup guide

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

You capture the coordinates from `calculate_url_route` and insert them as node metadata. LlamaIndex then indexes these coordinates, making your routing URLs searchable via vector queries.

Yes, the agent triggers `submit_vrp_optimizer` and indexes the final dispatch plan. This lets you run semantic queries against your optimized fleet schedules using this MCP Server.

The agent processes the raw output from `calculate_routing_matrix` and splits it into searchable document chunks. This makes your distance tables queryable by natural language.

Yes, you run GPX traces through the snapping tool first. This ensures the coordinate data you index in LlamaIndex matches actual road segments.

Your matrix data and address queries are sent via secure HTTPS to the GraphHopper API and never written to disk. The MCP Server sandbox ensures no local logging of your spatial data occurs.

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