How to Use the CARTO MCP in Google ADK

Q: Can Google ADK discover my existing CARTO maps?

Calling listmapdatasets pulls an array of every visualization and table in your organization. Your Gemini agent reads the privacy settings and row counts to audit your spatial assets. It knows exactly what data is available before writing any queries.

Q: How do CARTO file imports work in Google ADK pipelines?

You provide a public URL to importexternalfile and the server pulls the CSV or KML into your warehouse. The agent tracks progress via getimportstatus until the new managed table appears. This automates your external data ingestion completely.

Q: Does the routing tool consume my account credits?

Yes, every successful calculateroute request deducts from your LDS routing quota. You should restrict this tool using the toolnames filter if you want to prevent autonomous agents from burning through your balance.

Connect your Gemini agents to BigQuery spatial data using Google ADK to run complex routing and isoline operations on CARTO.

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 Google ADK

Create your Vinkius account to connect CARTO to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Native BigQuery spatial execution

The `execute_sql_query` tool runs arbitrary SQL straight against your BigQuery connection and feeds JSON rows back to your Gemini agent. Google ADK handles massive context windows easily, so you can dump thousands of coordinate pairs into the prompt. The agent reads the raw spatial data and plans its next move. Heavy multi-join transformations shift over to `create_async_sql_job` to bypass the 60-second timeout window. The agent fires the job off to the data warehouse and frees up the reasoning loop. It then uses `poll_async_job_status` to grab the updated timestamp when the computation finishes.

Bulk address resolution

Pushing CRM lists through `geocode_batch_addresses` converts massive text arrays into latitude and longitude coordinates in one shot. Your Gemini model parses the match quality indicators to flag any ambiguous locations. You stop wasting API calls on individual lookups. Single lookups still work perfectly via `geocode_address` when the agent just needs to place one new store location. The MCP Server routes the request through the LDS endpoint and returns the formatted address. Every operation runs safely through the Vinkius infrastructure.

Drive-time analysis with CARTO MCP Server

Your agent generates reachability contours by calling `calculate_isoline` with a specific time threshold in seconds. Gemini takes that GeoJSON polygon and cross-references it with existing BigQuery demographic tables. You get instant service area analysis without writing manual spatial queries. Calculating optimal paths happens through the `calculate_route` tool. The agent grabs the total distance in meters and plots the geometry on your map. This setup lets your Vertex AI pipelines coordinate physical logistics automatically.

Setup guide

Set up CARTO MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CARTO tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CARTO_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CARTO tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run pip install google-adk and set up a McpToolset using the StreamableHttpServerParameters class. You pass that toolset directly to your LlmAgent initialization. The MCP connection handles the actual routing to Vinkius.

Calling list_map_datasets pulls an array of every visualization and table in your organization. Your Gemini agent reads the privacy settings and row counts to audit your spatial assets. It knows exactly what data is available before writing any queries.

You provide a public URL to import_external_file and the server pulls the CSV or KML into your warehouse. The agent tracks progress via get_import_status until the new managed table appears. This automates your external data ingestion completely.

Yes, every successful calculate_route request deducts from your LDS routing quota. You should restrict this tool using the tool_names filter if you want to prevent autonomous agents from burning through your balance.

Vinkius isolates your database connection strings and routing API keys inside an ephemeral execution environment. The Gemini agent only sees the final GeoJSON outputs, never the underlying authentication logic. Your cloud infrastructure remains completely decoupled from the reasoning engine.

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