How to Use the HERE Mobility MCP in Pydantic AI

Q: How do I register the HERE Mobility MCP Server in Pydantic AI?

Install the pydantic-ai-slimmcp package. Create an MCPToolset pointing to your HTTP endpoint. Pass this toolset into your Agent constructor. Do not use the deprecated MCPServerHTTP class.

Q: Will Pydantic AI retry if HERE Mobility returns a bad route format?

Yes. If the agent receives a malformed response from discovertrips, Pydantic AI triggers a validation error. The framework can automatically prompt the LLM to correct its tool call or fail the operation entirely.

Q: How do I check for wheelchair accessibility at transit stops?

Your agent must first locate the stop using getnearbystations or getstations. It then passes the resulting station ID into the getstationdetails tool, which returns the facility information.

Type-safe transit routing for Pydantic AI. Validate HERE Mobility schedules and multimodal trips at runtime with zero silent failures.

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 Pydantic AI

Create your Vinkius account to connect HERE Mobility 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 HERE Mobility with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly validated transit routing

The `discover_trips` tool returns nested transit itineraries that Pydantic AI forces into strict data models. Public transit APIs return deeply messy JSON. If the API drops the transfer count or formats the departure time wrong, your agent fails loudly instead of hallucinating a route. Strict validation prevents broken commutes. The `search_multimodal_trips` endpoint returns complex arrays breaking down walking, biking, and subway segments. Your agent validates the exact duration of each leg before presenting the itinerary to the user.

Type-safe Pydantic AI station discovery

The `get_stations_by_name` tool turns a string like "Times Square" into a concrete station ID for your agent. You can't route a trip without an origin. It then feeds that validated ID into `get_station_details` to check for specific facilities. Using an MCP Server drops the integration entirely. You initialize `MCPToolset` with your endpoint, and Pydantic AI automatically maps all eight tools to your chosen LLM. It works exactly the same whether you use OpenAI, Anthropic, or a local Llama model.

Validate schedules via MCP Server

The `get_schedule` tool queries the next arriving trains for a specific platform and validates the timestamps. Transit apps die when they show outdated arrival times. Pydantic AI ensures the direction filters match your expected schema exactly. Once the agent confirms the schedule, it can pull the full path using `get_route_details`. You pass the original trip ID, and the agent maps every stop along the way. Your users get a mathematically correct commute plan every single time.

Setup guide

Set up HERE Mobility 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": {
        "here-mobility-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent HERE Mobility 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 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 Pydantic AI

Install the `pydantic-ai-slim[mcp]` package. Create an `MCPToolset` pointing to your HTTP endpoint. Pass this toolset into your Agent constructor. Do not use the deprecated `MCPServerHTTP` class.

Yes. If the agent receives a malformed response from `discover_trips`, Pydantic AI triggers a validation error. The framework can automatically prompt the LLM to correct its tool call or fail the operation entirely.

Absolutely. The framework is model-agnostic. As long as your local model supports tool calling, it can interact with `search_multimodal_trips` and the other endpoints just like GPT-4 would.

Your agent must first locate the stop using `get_nearby_stations` or `get_stations`. It then passes the resulting station ID into the `get_station_details` tool, which returns the facility information.

The MCP Server ingests raw user origins, destinations, and ISO 8601 timestamps. Vinkius secures this data by executing the code inside a stateless V8 sandbox. Authentication requires a single endpoint token, and the environment destroys itself immediately after the routing request completes.

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