How to Use the CARTO MCP in AutoGen

Q: How do AutoGen agents share CARTO SQL query results during a conversation?

Agents pass the JSON outputs of executesqlquery as text messages within their group chat. The receiving agent parses the rows to extract spatial coordinates or attributes for its own decisions.

Q: Can one AutoGen agent trigger a CARTO import while another monitors the status?

Yes, you can assign importexternalfile to an ingestion agent and getimportstatus to a monitoring agent. They communicate in the AutoGen group chat, with the monitor alerting the team once the import completes.

Enable AutoGen agent squads to debate routing logistics, execute spatial SQL, and coordinate CARTO data imports.

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 AutoGen

Create your Vinkius account to connect CARTO to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent routing debates in AutoGen

`calculate_route` and `calculate_isoline` provide the objective spatial data that your AutoGen agents use to resolve logistical disagreements. One agent proposes a delivery route, while another uses isolines to check if the destination falls within the acceptable travel-time threshold. They debate the options until they reach a consensus on the most efficient path. This collaborative loop ensures your planning is backed by real-world geometry. Your AutoGen agents negotiate trade-offs between distance and time, producing optimized decisions without manual intervention.

Manage heavy CARTO database tasks via AutoGen agents

`create_async_sql_job` and `poll_async_job_status` allow an AutoGen database agent to run intensive spatial queries while keeping other agents updated on progress. The database agent kicks off a heavy SQL job in BigQuery or Snowflake, then yields the floor to other agents. While the query runs, your coordination agents can draft reports or prepare other tasks. Once the polling agent confirms the job is done, it shares the final table name with the group. This allows the conversation to proceed with fresh, processed data.

Import and verify spatial datasets in this MCP Server

`import_external_file` and `geocode_address` let your AutoGen agents ingest raw files and confirm location accuracy before running analysis. An ingestion agent uploads a CSV file, while a QA agent checks the import status. If errors occur, the QA agent can geocode individual problematic addresses to fix the dataset. This division of labor prevents corrupted spatial data from reaching your main tables. Your agents work together to ensure only clean, verified coordinates are committed to your CARTO workspace.

Setup guide

Set up CARTO MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes CARTO tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="CARTO_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CARTO data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="CARTO_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CARTO data")
    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 AutoGen

Agents pass the JSON outputs of `execute_sql_query` as text messages within their group chat. The receiving agent parses the rows to extract spatial coordinates or attributes for its own decisions.

Yes, you can assign `import_external_file` to an ingestion agent and `get_import_status` to a monitoring agent. They communicate in the AutoGen group chat, with the monitor alerting the team once the import completes.

You use the AutoGen MCP adapter to fetch the tools from your Vinkius HTTP endpoint. You then pass the adapted tool list directly to the `AssistantAgent` constructor during initialization.

The tool returns an error message containing the failure details. Your AutoGen conversation manager routes this error back to the agent, which can then attempt to fix the coordinates or try an alternative query.

This MCP Server runs in a zero-trust, isolated V8 sandbox on Vinkius. Your SQL queries and raw address strings are sent directly to the CARTO API over secure HTTPS connections, ensuring no conversational logs or spatial coordinates are stored on the host.

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