How to Use the Mapbox MCP in LangChain

Q: How do I connect Mapbox to my LangChain agents?

Install langchain-mcp-adapters and langgraph. Configure MultiServerMCPClient with the Mapbox endpoint, pull the tool list, and pass it to createagent.

Q: Can LangChain agents chain Mapbox routing with internal databases?

Yes. Your agent can pull coordinates via geocode, feed them to a SQL database tool to check inventory, and then run getdirections on the result.

Build spatial reasoning pipelines by connecting Mapbox to your LangChain agents.

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 LangChain

Create your Vinkius account to connect Mapbox to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Mapbox routing in LangChain

The `get_directions` tool returns exact travel times, turn-by-turn maneuvers, and path geometry for driving, walking, or cycling. Your agent calls this tool to pull raw maneuver data directly into its working memory. This allows the framework to make immediate decisions based on actual transit conditions. You link this with `get_distance_matrix` to build logistics pipelines. The agent calculates travel times between multiple origins and destinations, then passes those matrices downstream to the next tool in your sequence. Every step is traceable, so you know exactly why the agent chose a specific route.

Wire location search into multi-step workflows

The `geocode` tool converts plain text addresses into precise bounding boxes and coordinates. Your LangChain agent grabs those coordinates and immediately feeds them into `search_nearby` to find restaurants or gas stations within a specific radius. The output of one tool becomes the direct input for the next. If you need to translate coordinates back to human-readable text, the agent hits `reverse_geocode`. LangSmith traces every coordinate lookup and API call this MCP Server makes, giving you total visibility into token usage and latency across the entire pipeline.

Feed spatial data into agent reasoning

The `get_isochrone` tool hands your agent polygon contours that define exact reachable areas based on travel time or distance. Your agent uses this output to determine service zones before making routing decisions. It evaluates the geometry and decides if a location falls within the valid operational boundary. You can also pull altitude data with `get_elevation` or generate a direct image URL via `get_static_map`. The agent decides which spatial tool to invoke based on intermediate results from previous chain steps, creating a highly dynamic location workflow.

Setup guide

Set up Mapbox MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Mapbox tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "mapbox-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Mapbox transactions"
    })
    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 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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Configure `MultiServerMCPClient` with the Mapbox endpoint, pull the tool list, and pass it to `create_agent`.

Yes. Your agent can pull coordinates via `geocode`, feed them to a SQL database tool to check inventory, and then run `get_directions` on the result.

LangSmith traces every request. You track exactly how many times your agent calls `get_distance_matrix` and monitor the latency to ensure you stay within your API limits.

LangGraph handles the multi-agent orchestration. You simply pass the Mapbox tools to the specific agent that needs spatial reasoning capabilities.

This server only processes the specific coordinates, addresses, and search queries (like "gas station") you pass to it. Vinkius isolates the execution environment, so your broader agent context and internal prompts stay completely private.

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