How to Use the CARTO MCP in Claude Code
Claude Code executes CARTO spatial queries via MCP Server right from your terminal.
Works with every AI agent you already use
…and any MCP-compatible client
Connect CARTO MCP to Claude Code
Create your Vinkius account to connect CARTO to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Terminal-Driven Spatial ETL
The `create_async_sql_job` tool lets your CLI agent trigger massive spatial transformations over the MCP protocol. You run a single command in your terminal to update materialized views across millions of rows. Claude Code fires the request and tracks the execution ID in the background. Your agent monitors progress via the `poll_async_job_status` tool without locking up your shell. You can pipe the final job status into a Slack notification script or a CI/CD pipeline. It handles the 60-second timeout limits by managing the asynchronous state entirely within your terminal session.
Command-Line Shapefile Imports
Claude Code pulls remote spatial files into your warehouse using the `import_external_file` tool. You pass a public URL containing a zipped shapefile or GeoJSON. The agent initiates the download and creates a new managed table in your database. To verify the ingestion, the agent calls `get_import_status` to check the progress percentage. Once the state hits complete, it uses `list_map_datasets` to confirm the new table exists. You automate your entire spatial data ingestion workflow without ever logging into a web console.
Headless Location Processing via MCP Server
The `geocode_batch_addresses` tool converts massive text files into coordinates through simple CLI prompts. You point the agent at a local CSV of CRM data. It reads the file, formats the payload, and hits the batch endpoint to process the entire list efficiently. For quick spot checks, Claude Code uses `geocode_address` to look up a single location. It returns the exact latitude and longitude straight to standard output. If you need catchment zones for those points, the agent chains the `calculate_isoline` tool to generate reachable area polygons on the fly.
Set up CARTO MCP in Claude Code
Prerequisites
- Claude Code CLI installed (
npm install -g @anthropic-ai/claude-code) - Active Vinkius subscription with a valid endpoint token
- 1
Run the add command
Open your terminal and run the command shown on the right. Replace
[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. Use--scope userto make it available across all projects. - 2
Verify the connection
Start a Claude Code session and type
/mcpto list connected servers. You should seecarto-mcpwith a green status indicator. - 3
Start using tools
Ask Claude Code something like "Check my latest CARTO transactions." It will automatically discover and invoke the available CARTO tools.
claude mcp add --transport http carto-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
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 Claude Code
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the CARTO MCP today
We host it, we monitor it, we maintain it. You just paste one token.