How to Use the GraphHopper MCP in Pydantic AI

Q: Does Pydantic AI validate the async polling responses from GraphHopper?

Yes. Every status check from pollvrpsolution is validated against strict schemas, ensuring your application always knows the exact state of the optimization job.

Q: Can I use this server to convert coordinates to addresses?

Yes. The reversegeocode tool extracts physical address properties, which are then validated into structured Python objects for immediate use.

Bring strict runtime type safety to your GraphHopper routing and geocoding workflows with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect GraphHopper to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Routing Matrices with Pydantic AI

Stop worrying about malformed API payloads breaking your logistics engine. This integration validates every coordinate and distance array returned by `calculate_routing_matrix` against strict Pydantic schemas. If the routing engine returns an unexpected coordinate format, your agent catches the validation error instantly. This prevents corrupted spatial data from poisoning your downstream planning databases.

Guaranteed VRP Optimization via MCP Server

Complex fleet distribution requires strict input validation before dispatching jobs. Your agent validates the vehicle and stop constraints before submitting them to `submit_vrp_optimizer`. While polling the status via `poll_vrp_solution`, the framework ensures that every intermediate state matches your exact data models. You get predictable, crash-proof fleet optimization.

Precise Isochrones and Road Snapping

Mapping delivery zones requires precise geometric outputs. The agent uses `calculate_distance_isochrone` to fetch travel boundaries, ensuring the returned polygon coordinates conform to strict GeoJSON types. The MCP Server handles raw tracking logs by feeding GPX traces into `snap_gpx_to_road`. The resulting snapped paths are validated at runtime, giving you clean, trusted spatial data for mileage calculations.

Setup guide

Set up GraphHopper MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "graphhopper-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to GraphHopper tools.",
)

result = await agent.run("List recent GraphHopper transactions")
print(result.output)

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 Pydantic AI

Create an MCPToolset with your server's HTTP URL and pass it to your Agent's toolsets parameter. The framework automatically parses the tool schemas.

The framework will immediately raise a validation error instead of passing bad coordinates to your agent. This guarantees that tools like `calculate_heavy_route` never pollute your application state.

Yes. Every status check from `poll_vrp_solution` is validated against strict schemas, ensuring your application always knows the exact state of the optimization job.

Yes. The `reverse_geocode` tool extracts physical address properties, which are then validated into structured Python objects for immediate use.

This MCP Server processes all routing matrices, vehicle profiles, and address strings in an isolated, ephemeral V8 sandbox. No data is stored, and the secure endpoint token prevents unauthorized access to your spatial pipelines.

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