An astronaut overseeing a futuristic data hub

Connect Radar to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your AI agent spatial intelligence and routing capabilities.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Radar.

  1. 01

    Autocomplete

    The autocomplete capability provides address or place suggestions as a user types.

  2. 02

    Ip geocode

    This capability retrieves geographic location information based on a specific IP address.

  3. 03

    Reverse geocode

    The reverse_geocode capability converts geographic coordinates into a human-readable address.

  4. 04

    Calculate route distance

    Use calculate_route_distance to find the travel distance and duration between two points.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Radar.

  1. 05

    Calculate routing matrix

    The calculate_routing_matrix capability computes travel times and distances across multiple origins and destinations.

  2. 06

    Forward geocode

    The forward_geocode capability converts a human-readable address into latitude and longitude coordinates.

  3. 07

    Get location context

    This capability pulls contextual data for a location, including weather and geofence information.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Radar.

  1. 08

    Search geofences

    The search_geofences capability finds active geofences located near a specific set of coordinates.

  2. 09

    Search places

    Use search_places to find nearby points of interest based on coordinates.

  3. 10

    Validate address

    The validate_address capability checks and cleans up structured address data.

Real work

What teams actually run

01

Logistics Optimization

An agent calculates travel times between multiple delivery points using a routing matrix.

02

Geofence Monitoring

The AI checks if a user's coordinates are inside a specific store boundary.

03

Data Cleaning

A developer uses the agent to validate and format messy address strings.

04

User Profiling

An agent uses IP geolocation to determine a user's general region.

Automate a task

Put Radar to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Radar works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Radar to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1027ms average. Fast in production.

Radar is checked daily against the live service.

Daily averagePeak 1242ms
Oct 3Today
Fastest day
866ms
Slowest day
1242ms
14-day trend
Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Radar, so you can see the experience inside your AI.

It does not authenticate your account with Radar. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Radar Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_eSpgWjdp768p0dPq7oo40SuSdNVfftLeN2IJW5wW/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Radar capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "radar-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_eSpgWjdp768p0dPq7oo40SuSdNVfftLeN2IJW5wW/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Radar in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Radar owners hand off.

This MCP is built for technical users who need to bridge the gap between text-based AI and physical location data.

  • 01

    Software Engineers

    They hand off coordinate debugging and distance verification to the agent.

  • 02

    Logistics Planners

    They use the agent to assess routing strategies and transit times.

  • 03

    Data Analysts

    They task the agent with converting raw IP inputs into specific regions or postal codes.

FAQ

Questions Radar owners ask.

  • 01

    How do I use Radar with Claude or Cursor?

    You connect the Radar MCP via Vinkius. Once connected, your AI client can immediately call the capabilities provided by the MCP.

  • 02

    Do I need my own API key?

    Yes, you will need to add your Radar Publishable API Key to the MCP configuration to enable the capabilities.

  • 03

    Can this MCP calculate driving times?

    Yes, it includes capabilities to calculate both the distance and the duration for travel between points.

  • 04

    Can the AI find my location using an IP address?

    Yes, the ip_geocode capability allows your agent to retrieve geographic information from an IP address.

  • 05

    What is the difference between forward and reverse geocoding?

    Forward geocoding turns an address into coordinates, while reverse geocoding turns coordinates into a readable address.

  • 06

    Where do I find my Radar API key?

    Log into your Radar dashboard. Under 'Project Settings' or the dedicated API keys section, look for your 'Publishable Key'. This is the standard read-only key used for client integrations and MCP operations.

  • 07

    Should I use the Publishable Key or the Secret Key?

    Always use the Publishable Key for this MCP server instance if possible, as the operations (geocoding, routing, lookup) are typically safe read-only spatial actions.

  • 08

    Can it calculate multi-stop routes like a delivery app?

    Yes, but indirectly through distance comparisons. The basic routing API fetches times from Point A to Point B. The AI can chain these requests together to establish an estimated schedule contextually in your chat.

Connect Radar to Claude, Cursor, ChatGPT & more