How to Use the Mapflow MCP in LlamaIndex

Q: How do I index GeoJSON from Mapflow in LlamaIndex?

After your LlamaIndex agent gets the data from getprocessingresult, you'll use a LlamaIndex data connector or a simple node parser. This converts the geospatial features into documents for your vector index.

Q: Can I build a LlamaIndex agent to query past Mapflow projects?

Absolutely. Have your agent periodically call listprojects and listprocessings, then index the metadata. This creates a searchable log of all activity on your MCP server.

Q: How does LlamaIndex handle the asynchronous nature of Mapflow jobs?

You'd typically wrap the polling logic for getprocessingstatus inside a custom LlamaIndex tool. The agent calls the tool, which handles the waiting internally before returning the final result.

Index geospatial data from satellite imagery using Mapflow and LlamaIndex for powerful, grounded RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapflow MCP to LlamaIndex

Create your Vinkius account to connect Mapflow 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 Mapflow with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Imagery Analysis into Knowledge

Stop treating analysis results as one-off files. Use `create_processing` to extract building footprints, then feed the GeoJSON from `get_processing_result` directly into a LlamaIndex vector store. The data is now a permanent, searchable asset. This allows you to ask questions in plain English, like "what was the building count in the downtown sector analysis from May?" Your agent finds the answer because it's grounded in the actual geospatial data you indexed, not just guessing.

Create a Geospatial Query Engine

Your agent can use `list_projects` and `list_processings` to build a complete, queryable index of your team's entire Mapflow history. It's like giving your agent a perfect memory of every analysis ever run. Now you can retrieve past configurations instantly. Ask your agent, "what model from `list_models` did we use for the airport job?" and it will pull the exact project details from your knowledge base.

Build RAG with this LlamaIndex MCP Server

The point here isn't just calling tools—it's making the tool outputs part of your agent's brain. After running `create_processing` and waiting with `get_processing_status`, the output from `get_processing_result` becomes a new document in your RAG index. Your agent can then compare new analysis against historical data it has already indexed. This is how you build systems that track urban growth or environmental changes over time, with every answer backed by facts from tool calls.

Setup guide

Set up Mapflow 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 Mapflow 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 Mapflow tools.",
)
response = await agent.run("List recent Mapflow 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 Mapflow. 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 Mapflow 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 Mapflow MCP in LlamaIndex

After your LlamaIndex agent gets the data from `get_processing_result`, you'll use a LlamaIndex data connector or a simple node parser. This converts the geospatial features into documents for your vector index.

Absolutely. Have your agent periodically call `list_projects` and `list_processings`, then index the metadata. This creates a searchable log of all activity on your MCP server.

A script just gets data. A LlamaIndex agent gets data, indexes it, and makes it part of a persistent, searchable knowledge base you can query with natural language.

You'd typically wrap the polling logic for `get_processing_status` inside a custom LlamaIndex tool. The agent calls the tool, which handles the waiting internally before returning the final result.

Mapflow processes your imagery within an isolated environment provided by Vinkius. The GeoJSON output from `get_processing_result` is sent to your LlamaIndex agent; securing the vector index where you store that data is your responsibility.

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