How to Use the CARTO MCP in LangChain

Q: How do I pass CARTO coordinates from a geocoding tool to a routing tool in LangChain?

You feed the output of geocodeaddress directly into the input parameters of calculateroute within your LangChain chain. The agent extracts the latitude and longitude from the geocoded JSON and uses them to define the route start or end points.

Q: What is the best way to handle long-running spatial queries in LangChain without timing out?

Use the createasyncsqljob tool inside a LangChain custom runnable or stateful graph. This allows your agent to submit the query, receive a job ID, and poll pollasyncjobstatus periodically while letting other chain steps run.

Build spatial reasoning chains in LangChain that query CARTO tables, generate drive-time isolines, and map routing coordinates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CARTO MCP to LangChain

Create your Vinkius account to connect CARTO 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 CARTO with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain route planning and isolines in LangChain

`calculate_route` and `calculate_isoline` provide the spatial geometry your LangChain agent needs to run multi-step location analysis. You pass the output of a route calculation straight into an isoline generator to find service areas along a delivery path. LangSmith traces every step, showing you exact coordinate payloads and API latency. Your chains make decisions on the fly. If a route exceeds a specific duration, your LangChain agent automatically triggers alternative calculations to find closer distribution hubs. You get structured GeoJSON back, ready to pass to the next node in your agentic workflow.

Run heavy CARTO SQL queries through LangChain agents

`create_async_sql_job` and `poll_async_job_status` allow your LangChain chains to run complex spatial queries without hitting timeout limits. This setup prevents your agent from freezing during massive BigQuery or Snowflake operations. You start a job, let the chain poll the status, and get the results once the warehouse finishes processing. For faster lookups, the agent switches to `execute_sql_query` to fetch instant spatial joins. This dual-path approach keeps your LangChain pipelines fast and cost-effective.

Ingest and geocode address lists using this MCP Server

`geocode_batch_addresses` and `import_external_file` let your LangChain agent pull raw files and convert them into clean, geocoded spatial datasets. The agent takes a raw CSV URL, uploads it to your warehouse, and runs batch geocoding to append coordinates. This MCP Server handles the connection details so your LangChain chain only manages the logic. You get back table names and status updates, allowing your pipeline to transition from raw data ingestion to active spatial analysis.

Setup guide

Set up CARTO 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 CARTO 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({
    "carto-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 CARTO 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 CARTO. 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 CARTO 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 CARTO MCP in LangChain

You feed the output of `geocode_address` directly into the input parameters of `calculate_route` within your LangChain chain. The agent extracts the latitude and longitude from the geocoded JSON and uses them to define the route start or end points.

Yes, LangSmith tracks the exact payload returned by tools like `calculate_route` or `geocode_batch_addresses`, which includes LDS credit consumption details. You can monitor these JSON responses in your LangChain execution logs to keep tabs on your CARTO billing.

Use the `create_async_sql_job` tool inside a LangChain custom runnable or stateful graph. This allows your agent to submit the query, receive a job ID, and poll `poll_async_job_status` periodically while letting other chain steps run.

Install the LangChain MCP adapter package and initialize the client with your Vinkius endpoint. You then fetch the tools and bind them to your chat model or agent executor.

This MCP Server runs in a secure, ephemeral V8 sandbox where your API keys and geocoded coordinates are never stored. Your SQL query strings and geographic coordinates pass directly to CARTO and your connected data warehouse over encrypted HTTPS connections.

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