How to Use the ArcGIS MCP in LlamaIndex

Q: Can I index travel times from ArcGIS into a LlamaIndex vector store?

Yes. You can run calculateodmatrix to generate travel times, then ingest that raw matrix data into a LlamaIndex Document object to make it searchable via semantic query.

Q: How does LlamaIndex handle coordinate bias with ArcGIS?

You can use suggestlocationbias to bias address autocomplete suggestions based on the user's current location stored in the LlamaIndex query context, ensuring more relevant local results.

Index live ArcGIS spatial data directly into your LlamaIndex vector store for grounded RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ArcGIS MCP to LlamaIndex

Create your Vinkius account to connect ArcGIS 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 ArcGIS with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Spatial Knowledge Bases with LlamaIndex

Turn geography into searchable knowledge. Your LlamaIndex agent can run `calculate_service_area` and index the resulting drive-time polygons directly into a vector database, turning this MCP tool output into structured information. Instead of querying raw GIS databases every time, your application searches past spatial computations. This turns expensive geometric calculations into fast, local semantic lookups.

Ground RAG Answers in Real ArcGIS MCP Server Data

Stop your agent from hallucinating routes and coordinates. When a user asks about nearby facilities, LlamaIndex uses `reverse_geocode` to resolve coordinates to physical addresses, feeding the real-world results directly into the LLM context. This ensures every location-based answer your agent gives is backed by actual spatial data. You get highly accurate local answers without worrying about the model making up fictional street names.

Smart Coordinate Filtering for Index Queries

Narrow down your search space before you query. By using this MCP Server to limit queries with `find_address_country`, LlamaIndex filters out irrelevant global data before indexing or retrieving. This targeted indexing means your vector store stays clean and highly relevant. You avoid mixing up identical street names in different countries, which keeps your semantic search results sharp.

Setup guide

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

Yes. You can run `calculate_od_matrix` to generate travel times, then ingest that raw matrix data into a LlamaIndex Document object to make it searchable via semantic query.

You can use `suggest_location_bias` to bias address autocomplete suggestions based on the user's current location stored in the LlamaIndex query context, ensuring more relevant local results.

Yes. By using the async tool list export in LlamaIndex, your agent can fire off multiple `batch_geocode_addresses` requests concurrently, speeding up large-scale ingestion pipelines.

Initialize the basic client with your Vinkius URL, wrap it in McpToolSpec, and call the tool list generator to register all ten spatial tools with your LlamaIndex agent.

Vinkius processes all spatial coordinates and addresses in a zero-trust, isolated environment. Your raw location parameters are never cached or written to persistent storage, protecting sensitive user telemetry.

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