How to Use the Mapbox MCP in CrewAI

Q: How do I configure CrewAI to use Mapbox?

Install the tools package via pip install crewaitools. Add your MCP server URL directly to the mcps array in your Agent definition.

Q: Can CrewAI agents share Mapbox routing data?

Yes. When one agent runs getdirections, the step-by-step maneuver data enters the crew's shared memory. Subsequent agents read those directions to draft driver instructions.

Q: How do I restrict which Mapbox tools my CrewAI agents can use?

Use MCPServerHTTP from crewai.mcp. You configure a toolfilter to only expose the geocode and searchnearby MCP tools to specific research agents.

Give your CrewAI agents advanced spatial awareness and routing with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapbox MCP to CrewAI

Create your Vinkius account to connect Mapbox 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 Mapbox with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate fleets with the Mapbox MCP Server

The `get_distance_matrix` tool computes travel times across dozens of origin and destination pairs simultaneously. Your dispatcher agent uses this to evaluate fleet positioning in real-time. You assign a secondary analyst agent to review this data. They cross-reference the matrix output and decide which driver gets the next assignment based on actual drive time.

Execute autonomous geographic research

The `search_nearby` tool finds specific points of interest around a target coordinate. Your research agent scans an entire neighborhood for gas stations or hotels instantly. Once the agent finds a location, it passes the coordinates to `get_elevation`. This proves highly effective for planning drone deliveries or analyzing terrain constraints without human input.

Map accessibility zones automatically

The `get_isochrone` tool generates reachable area polygons based on walking, cycling, or driving profiles. A planning agent requests this data to determine service coverage boundaries. When combined with `reverse_geocode`, your CrewAI setup identifies exactly which neighborhoods fall outside your delivery zones. The agent then drafts expansion reports automatically.

Setup guide

Set up Mapbox 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 Mapbox tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Mapbox 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="Mapbox Analyst",
        goal="Access and analyze Mapbox data via MCP.",
        backstory="Expert analyst with direct Mapbox access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Mapbox 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 Mapbox. 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 Mapbox 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 Mapbox MCP in CrewAI

Install the tools package via `pip install crewai[tools]`. Add your MCP server URL directly to the `mcps` array in your Agent definition.

Yes. When one agent runs `get_directions`, the step-by-step maneuver data enters the crew's shared memory. Subsequent agents read those directions to draft driver instructions.

Use `MCPServerHTTP` from `crewai.mcp`. You configure a `tool_filter` to only expose the `geocode` and `search_nearby` MCP tools to specific research agents.

The routing tools accept profile parameters. Your agents specify `mapbox/walking` or `mapbox/cycling` when calling the API to get accurate non-driving paths.

Vinkius destroys the MCP execution environment after every single request. Your point-of-interest queries and exact coordinate pairs process entirely in memory and vanish immediately.

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