How to Use the Jawg Maps (Location & Routing) MCP in LangChain

Q: How do I connect Jawg Maps (Location & Routing) to my LangChain agent?

Install the adapter package first. Run pip install langchain-mcp-adapters langgraph in your terminal. Then, initialize MultiServerMCPClient pointing to your Vinkius MCP endpoint and pass the tools directly to your agent constructor.

Q: How does Jawg Maps (Location & Routing) handle address autocompletion in LangChain?

The agent uses searchautocomplete to resolve partial user inputs into coordinates. It can bias these search results toward a specific GPS location to ensure local accuracy. This prevents the agent from guessing random global addresses.

Q: Can I filter location searches by country?

Use the searchcountryfilter tool to restrict all address lookups to specific regions. Your agent passes the country code parameter to keep search results clean and relevant. This cuts down on processing overhead for international setups.

Give your LangChain chains real-world spatial intelligence with Jawg Maps routing and search tools using this dedicated 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 Jawg Maps (Location & Routing) MCP to LangChain

Create your Vinkius account to connect Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Routing and Geocoding in LangChain

This MCP server exposes `calculate_routing_line` directly to your LangChain agent so it can plot routes across multiple waypoints on the fly. Your agent reads the user's location input, calls the tool, and feeds the coordinates straight into the next step of your chain. No hardcoded logic is needed to handle complex routing requests. You get full visibility into these spatial operations through LangSmith tracing. Every time your agent triggers `reverse_geocode` to turn raw coordinates into a street address, you see the exact payload and latency. This makes debugging multi-step spatial chains incredibly straightforward.

Calculate Delivery Areas on the Fly

The `calculate_reachability_isochrone` tool lets your agent determine how far a driver can travel within a strict time limit. This is highly useful when building dispatch agents that need to filter out-of-bounds requests before they even hit your database. The agent checks the reachability polygon and routes the task accordingly. For distance-based limits, the agent runs `calculate_distance_isochrone` to get the exact boundary line. It handles these calculations in parallel with other chain steps. You end up with a fast, deterministic way to qualify locations before committing resources.

Build Complex Distance Matrices

Running `calculate_distance_matrix` via this MCP server allows your LangChain agent to compute travel times and distances between dozens of origins and destinations in one go. The output feeds directly into your optimization chains. This replaces slow, sequential API calls with a single, structured operational step. When elevation matters for fuel or physical effort, the agent pairs this with `calculate_elevation_routing` to plan the path. It analyzes the climbs and descents to choose the most efficient route. Your agent manages this entire flow dynamically based on the goals you set in your prompt.

Setup guide

Set up Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) 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({
    "jawg-maps-location-routing-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 Jawg Maps (Location & Routing) 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 Jawg Maps. 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 Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) MCP in LangChain

Install the adapter package first. Run `pip install langchain-mcp-adapters langgraph` in your terminal. Then, initialize `MultiServerMCPClient` pointing to your Vinkius MCP endpoint and pass the tools directly to your agent constructor.

Yes, the agent handles this natively using ReAct loops. It will call `search_map_places` to find an address, then pass those coordinates to `calculate_routing_line` in the very next step. LangSmith tracks the entire sequence so you can monitor latency.

The agent uses `search_autocomplete` to resolve partial user inputs into coordinates. It can bias these search results toward a specific GPS location to ensure local accuracy. This prevents the agent from guessing random global addresses.

Use the `search_country_filter` tool to restrict all address lookups to specific regions. Your agent passes the country code parameter to keep search results clean and relevant. This cuts down on processing overhead for international setups.

This server processes coordinate strings and physical addresses only when executing active tool calls. Vinkius runs the code in an isolated V8 sandbox that destroys all memory states immediately after the request finishes. No location history or route coordinates are stored on our servers.

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