How to Use the Radar MCP in LlamaIndex

Q: How do I index physical coordinates retrieved from Radar into LlamaIndex?

Use forwardgeocode to convert raw addresses into coordinates, then wrap that payload in a LlamaIndex TextNode. You can store these coordinates as metadata keys to enable hybrid spatial-semantic queries.

Q: Can LlamaIndex query engines use Radar to resolve user locations from IP addresses?

Yes, the query engine can call ipgeocode at the start of a query pipeline to detect the user's city. This lets LlamaIndex filter the indexed documents so it only retrieves localized search results.

Q: How do I set up the Radar MCP Server tools inside LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient with the server's endpoint. Convert the client tools using McpToolSpec and pass them directly to your LlamaIndex FunctionAgent.

Q: Can I use Radar autocomplete to help users search my LlamaIndex knowledge base?

Yes, you can expose the autocomplete tool to your agentic query pipeline. When a user types a partial query, the tool suggests matching addresses, which the agent then uses to query your indexed geographical data.

Q: How does this MCP Server protect sensitive IP addresses and coordinates in LlamaIndex?

All IP addresses and coordinates processed by ipgeocode and reversegeocode pass through secure, ephemeral Vinkius sandboxes. The raw telemetry is never stored or written to disk, ensuring strict compliance with spatial privacy standards.

Index live Radar spatial data directly into LlamaIndex vector stores to ground your RAG queries in physical reality.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Radar MCP to LlamaIndex

Create your Vinkius account to connect Radar to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Radar with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index spatial contexts into LlamaIndex vector stores

Stop letting your RAG pipelines hallucinate physical locations. This MCP Server lets LlamaIndex query `get_location_context` and `search_places` to pull real-time point-of-interest data and geofence contexts, instantly converting them into searchable document nodes. Your index stays grounded in actual physical geography. When a user asks about local services, the engine queries the vector store for cached locations and uses `search_geofences` to verify immediate spatial relationships.

Resolve and index raw addresses with LlamaIndex

Messy location data ruins semantic search. Your LlamaIndex pipeline uses the MCP tool `validate_address` to clean up incoming address strings and standardizes them before they ever touch your vector database. By combining `forward_geocode` with your indexing runs, you store exact latitude and longitude coordinates alongside raw text documents. This lets your query engine perform precise spatial filtering on top of traditional vector search.

Dynamic routing lookups inside LlamaIndex query engines

Let your query engine calculate real-world travel times on the fly. The pipeline triggers `calculate_route_distance` to measure the actual driving distance between indexed coordinate nodes during the retrieval phase. For complex multi-stop lookups, the engine uses `calculate_routing_matrix` to compare distances across several indexed locations. This injects real-world logistics metrics directly into your synthetic text responses.

Setup guide

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

Use `forward_geocode` to convert raw addresses into coordinates, then wrap that payload in a LlamaIndex TextNode. You can store these coordinates as metadata keys to enable hybrid spatial-semantic queries.

Yes, the query engine can call `ip_geocode` at the start of a query pipeline to detect the user's city. This lets LlamaIndex filter the indexed documents so it only retrieves localized search results.

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient` with the server's endpoint. Convert the client tools using `McpToolSpec` and pass them directly to your LlamaIndex `FunctionAgent`.

Yes, you can expose the `autocomplete` tool to your agentic query pipeline. When a user types a partial query, the tool suggests matching addresses, which the agent then uses to query your indexed geographical data.

All IP addresses and coordinates processed by `ip_geocode` and `reverse_geocode` pass through secure, ephemeral Vinkius sandboxes. The raw telemetry is never stored or written to disk, ensuring strict compliance with spatial privacy standards.

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