How to Use the HERE Mobility MCP in CrewAI

Q: How do I assign different HERE Mobility tools to different agents in CrewAI?

You can use the toolfilter option when defining your MCPServerHTTP connection in CrewAI. This lets you give a "Scout" agent access to only getstations, while a "Planner" agent gets access to discovertrips. This enforces role specialization.

Q: Can a CrewAI team build a complete travel itinerary using HERE Mobility?

Yes. One agent can find stations (getnearbystations), a second can plan the main trip (discovertrips), and a third can check schedules (getschedule) for each transfer point. The final output is a coordinated plan built by a team of agents.

Q: Can I use this MCP server for just walking or biking routes?

The searchmultimodaltrips tool is designed for this. Your CrewAI agent can request routes that specifically combine walking, biking, and even scooters with public transit, or just stick to those modes if you prefer.

Q: How is data like my location handled when my CrewAI agents use the HERE Mobility MCP server?

Each tool call is stateless. When an agent calls discovertrips, the origin and destination coordinates are sent to the MCP server for that single request and then discarded. The Vinkius platform guarantees that no personal location data or trip history is ever stored.

Deploy autonomous transit planning crews. Your CrewAI agents can now research, plan, and monitor public transit using HERE Mobility tools.

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 CrewAI

Create your Vinkius account to connect HERE Mobility to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialize Your CrewAI Agents

Assign specific roles to your CrewAI agents for complex transit tasks. A "Scout Agent" can use `get_nearby_stations` and `get_stations_by_name` to map out all the transit options in an area. It then passes its findings to the next agent. A "Route Planner Agent" takes the scout's data and uses the more intensive `discover_trips` and `search_multimodal_trips` tools to find the most efficient routes. By splitting the tasks, you use the right tool for the right job, and your crew works faster.

Build Autonomous Monitoring Crews

Set up a crew to monitor a commute. A "Scheduler Agent" can be tasked with repeatedly calling `get_schedule` for a specific station and route. Its only job is to watch for delays or cancellations. If the Scheduler detects a problem, it alerts a "Re-Router Agent." This second agent wakes up, gets the original trip details with `get_route_details`, and immediately runs a new `discover_trips` search to find an alternative. The crew just solved a problem without any human input.

Hierarchical Trip Analysis with CrewAI

Use CrewAI's hierarchical structure for deep analysis. A manager agent could be tasked with finding the "best" way from A to B. It could delegate tasks to subordinate agents: one finds the fastest route with `discover_trips`, another finds the one with fewest transfers using `search_multimodal_trips`, and a third finds the cheapest. The manager agent then collects the reports from each specialist agent—which include detailed data from `get_route_details`—and makes a final recommendation. This is how you move from simple queries to genuine automated decision-making with this MCP server.

Setup guide

Set up HERE Mobility MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke HERE Mobility tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="HERE Mobility Analyst",
    goal="Access and analyze HERE Mobility data via MCP.",
    backstory="Expert analyst with direct HERE Mobility access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent HERE Mobility transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="HERE Mobility Analyst",
        goal="Access and analyze HERE Mobility data via MCP.",
        backstory="Expert analyst with direct HERE Mobility access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent HERE Mobility transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can use the `tool_filter` option when defining your `MCPServerHTTP` connection in CrewAI. This lets you give a "Scout" agent access to only `get_stations`, while a "Planner" agent gets access to `discover_trips`. This enforces role specialization.

Yes. One agent can find stations (`get_nearby_stations`), a second can plan the main trip (`discover_trips`), and a third can check schedules (`get_schedule`) for each transfer point. The final output is a coordinated plan built by a team of agents.

It's about parallelism and specialization. CrewAI lets you run multiple agents, each with a focused task using specific HERE Mobility tools. This allows you to build autonomous systems that can research, plan, and react to transit issues all at once.

The `search_multimodal_trips` tool is designed for this. Your CrewAI agent can request routes that specifically combine walking, biking, and even scooters with public transit, or just stick to those modes if you prefer.

Each tool call is stateless. When an agent calls `discover_trips`, the origin and destination coordinates are sent to the MCP server for that single request and then discarded. The Vinkius platform guarantees that no personal location data or trip history is ever stored.

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