How to Use the CARTO MCP in LlamaIndex

Q: How do I index CARTO SQL query results into a LlamaIndex vector store?

You run executesqlquery to retrieve your spatial rows, then wrap the JSON output in LlamaIndex Document objects. From there, your pipeline passes them to an ingestion pipeline to generate embeddings and store them in your vector database.

Q: Can LlamaIndex query past route calculations to save CARTO LDS credits?

Yes, you can index the GeoJSON outputs from calculateroute into your LlamaIndex vector store. Before calling the live API, your agent performs a semantic search over the index to see if a similar route already exists.

Q: What file formats can I import into my database using this setup?

The importexternalfile tool supports CSV, GeoJSON, zipped Shapefiles, KML, GPX, and Excel files. Your agent can trigger the import and track its progress automatically.

Index CARTO spatial datasets, routes, and isolines directly into LlamaIndex vector stores for context-rich RAG.

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 LlamaIndex

Create your Vinkius account to connect CARTO to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index CARTO spatial query results into LlamaIndex

`execute_sql_query` and `list_map_datasets` allow your LlamaIndex pipeline to fetch active database layers and convert them into searchable document nodes. The agent queries your spatial tables, fetches geographic records, and indexes them into a vector store. This lets you run semantic search queries over actual physical locations and attributes. Your RAG applications gain immediate access to real-time warehouse data. Instead of relying on static files, LlamaIndex pulls fresh records directly from your CARTO connection to answer complex geographic questions.

Store and query routing geometries in LlamaIndex

`calculate_route` and `calculate_isoline` provide physical travel geometries that LlamaIndex indexes to ground agent decisions in real-world distances. When your agent needs to evaluate warehouse placement, it pulls existing isoline data from the index to check reachability. This prevents the model from generating hallucinated routes or impossible travel times. The indexed GeoJSON structures remain fully searchable. You can query past route calculations directly from your vector database, saving API credits on redundant spatial computations.

Geocode and index address lists using this MCP Server

`geocode_batch_addresses` and `get_import_status` let your LlamaIndex workflows process bulk location lists and immediately index the coordinates. You pass raw address strings from your documents, geocode them in bulk, and append the spatial coordinates to your index metadata. This MCP Server handles the heavy lifting of talking to CARTO's LDS engine. Your LlamaIndex agent simply receives clean, structured JSON, making it easy to build location-aware search indexes.

Setup guide

Set up CARTO MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all CARTO MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to CARTO tools.",
)
response = await agent.run("List recent CARTO data")

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 LlamaIndex

You run `execute_sql_query` to retrieve your spatial rows, then wrap the JSON output in LlamaIndex Document objects. From there, your pipeline passes them to an ingestion pipeline to generate embeddings and store them in your vector database.

Yes, you can index the GeoJSON outputs from `calculate_route` into your LlamaIndex vector store. Before calling the live API, your agent performs a semantic search over the index to see if a similar route already exists.

You use the LlamaIndex MCP tool spec package to load the tools from your Vinkius server URL. Once loaded, you pass the tool list directly to your `FunctionAgent` or `ReActAgent` constructor.

The `import_external_file` tool supports CSV, GeoJSON, zipped Shapefiles, KML, GPX, and Excel files. Your agent can trigger the import and track its progress automatically.

This MCP Server operates inside a zero-trust, isolated V8 sandbox that keeps your SQL code and geocoded address strings private. All payloads transit directly between your LlamaIndex environment and CARTO's servers over secure TLS connections, with no persistent logging of your spatial coordinates.

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