How to Use the HERE Mobility MCP in AutoGen

Q: Can I have one AutoGen agent find a station and another get its schedule with HERE Mobility?

Absolutely. A 'Finder' agent would use getstationsbyname to get a station ID. It then passes that ID to a 'Scheduler' agent in the conversation, which in turn uses getschedule to fetch the departure times.

Orchestrate multi-agent transit planning with AutoGen. Let specialized agents debate HERE Mobility routes and reach a consensus.

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 AutoGen

Create your Vinkius account to connect HERE Mobility to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Route Deliberation

AutoGen lets you build a team of agents to plan a trip. A 'Speed' agent might call `discover_trips` and argue for the fastest option. A 'Comfort' agent could use the same tool's output but argue against routes with too many transfers. They debate in a conversation. The 'Comfort' agent might counter by calling `search_multimodal_trips` to find a slightly slower but simpler route with a single bus and a short walk. The final plan is a consensus, not a single-shot API call.

Specialized Agents for Complex Tasks

Assign roles. One agent's only job is station logistics; it uses `get_nearby_stations` and `get_stations_by_name` to find valid start and end points. A second 'Scheduler' agent takes those station IDs and uses `get_schedule` to check timings. This separation of concerns makes your system more robust. If the 'Station' agent can't find a location, the conversation stops before the 'Scheduler' agent even tries to run. It's like a small, automated team meeting to plan a trip.

Validate Trip Plans with an AutoGen Critic Agent

One agent proposes a plan, another critiques it. The 'Planner' agent calls `discover_trips` to generate an itinerary. Then, a 'Validator' agent takes that trip ID and uses `get_route_details` to double-check every leg of the journey. The 'Validator' can flag potential issues, like a short transfer time or a long walk between connections, which it identifies from the detailed route data. This adversarial setup, powered by this MCP Server, produces more reliable travel plans.

Setup guide

Set up HERE Mobility MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes HERE Mobility tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="HERE Mobility_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent HERE Mobility data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="HERE Mobility_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent HERE Mobility data")
    print(result.messages[-1].content)

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 AutoGen

Create two agents with different system prompts, like one prioritizing speed and another minimizing transfers. Give both access to the HERE Mobility tools. They'll call `discover_trips`, analyze the results from their own perspective, and argue until they agree on a plan.

Absolutely. A 'Finder' agent would use `get_stations_by_name` to get a station ID. It then passes that ID to a 'Scheduler' agent in the conversation, which in turn uses `get_schedule` to fetch the departure times.

You could have a 'Bicycle' agent and a 'Transit' agent. They can both analyze the output of `search_multimodal_trips` to debate the pros and cons of different bike-plus-train combinations for a daily commute, reaching a balanced recommendation.

You provide the list of tools from the MCP server to the agents that need them. AutoGen's conversational flow determines when a tool is called. An agent must propose a valid tool call, like using `get_route_details`, which is then executed.

The agents exchange trip details, station names, and coordinates sourced from the HERE Mobility server. Vinkius isolates each request in a dedicated V8 sandbox. The connection is authenticated via a single token, and no transit query data is ever logged or stored by the server instance.

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