How to Use the CARTO MCP in Cline

Give Cline the ability to execute spatial SQL and build map components from CARTO through 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 CARTO MCP to Cline

Create your Vinkius account to connect CARTO to Cline 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 Cline

Ask AI about this MCP

ChatGPT

Claude

Perplexity

End-to-End CARTO MCP Server Workflows

The `execute_sql_query` tool gives Cline direct read access to your spatial data warehouse. You tell the agent to build a dashboard showing regional sales. Cline queries the database, gets the JSON rows, and writes the entire React map component in your workspace. It doesn't stop at reading data. If you need a new layer, Cline uses `import_external_file` to ingest a shapefile URL. The agent creates the file, writes the API integration code, and stages the commit for you. You get a working map application without writing the boilerplate.

Batch Geocoding and Path Generation

Cline processes raw customer lists by feeding them into the `geocode_batch_addresses` tool. You drop a messy CSV of store locations into VS Code. The agent reads the file, hits the CARTO API, and replaces the raw text with precise latitude and longitude coordinates. For logistics applications, the agent calls `calculate_route` to get driving directions and distance metrics. It writes the backend logic to handle the GeoJSON output. If you need a single location checked during debugging, Cline fires off `geocode_address` to verify the coordinates instantly.

Autonomous Isoline Creation

The `calculate_isoline` tool allows Cline's MCP connection to generate travel-time polygons directly from your editor. You ask for a 10-minute walk time around a specific point. The agent fetches the GeoJSON contour and immediately implements it into your deck.gl visualization layer. When building ETL pipelines, Cline handles heavy computations through `create_async_sql_job`. It writes the polling logic using `poll_async_job_status` to ensure your application waits for the data warehouse to finish processing. The agent builds resilient spatial applications by understanding how long-running database operations actually work.

Setup guide

Set up CARTO MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type carto-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest CARTO refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "mcpServers": {
    "carto-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cline

Open the VS Code sidebar and click the server icon. Navigate to the Remote Servers tab and paste your Vinkius Streamable HTTP URL. Cline connects instantly and exposes the geocoding and routing tools to your workspace.

The agent reads your spatial tables and writes the frontend code to visualize them. It pulls the exact column names using the dataset listing tool. You get fully functional map layers without manually checking your database schema.

It submits heavy spatial joins as asynchronous batch jobs. The agent knows to poll the job status rather than blocking your editor. Once the warehouse finishes, Cline pulls the results and continues building your application.

Yes, routing and geocoding operations use your account's LDS credits. The agent calls the official APIs powered by TomTom or HERE. You control the usage by setting clear instructions on how many addresses it should process.

Your fleet logistics and driving routes pass through a strictly isolated environment. We run the connection inside a temporary sandbox that blocks all external network requests outside the target API. The entire execution context is wiped from memory the moment the response is delivered.

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