developer-toolsapi_key

Radar

Radar is a full-stack location infrastructure platform offering SDKs and APIs for geofencing, location tracking, geocoding, search, routing, and maps.

Verdict

Radar brings location intelligence into your workspace — forward and reverse geocoding, geofence management, trip tracking, and place context lookups. @mention Radar to convert addresses to coordinates, autocomplete partial inputs, check what geofences or points of interest surround a lat/long, or create and delete trips. Engineering teams building location features, ops teams routing deliveries, and support teams debugging user-reported addresses get the most value. Requires an API key from your Radar dashboard; all 24 tools run server-side so no user location permissions needed.

Common use cases

  • Validate customer shipping addresses at checkout
  • Autocomplete venue names during event planning
  • Check geofence coverage for delivery zones
  • Debug location bugs from support tickets
  • Track trip progress for logistics coordination

Integration

Vendor
Radar
Category
developer-tools
Auth
API_KEY
Tools
24
Composio slug
radar

Tools

  • Autocomplete Address or Place

    Tool to autocomplete partial addresses and place names based on relevance and proximity. use after a user inputs a partial address/place to get suggestions, optionally biased by location.

  • Create Trip

    Tool to create a new trip. use after gathering origin and destination details to start tracking a trip.

  • Delete Geofence
    destructive

    Tool to delete a geofence by id. use when supplying a geofence’s unique identifier to remove it.

  • Delete Trip
    destructive

    Tool to delete a trip by its radar id or external id. use after confirming the trip exists.

  • Forward Geocode

    Tool to convert an address into geographic coordinates. use when you have a full address string and need precise latitude/longitude before further location analysis.

  • Get Context for Location

    Tool to retrieve context for a given location. use when you need geofences, place, and region information based on coordinates. use after obtaining valid latitude and longitude.

  • Get Geofence

    Tool to retrieve a geofence by radar id or tag/externalid. use when you need to fetch full details of an existing geofence.

  • Get Places Settings

    Tool to retrieve current places settings for your radar project. use when you need to inspect chain detection, supported countries, external id requirements, and other places metadata.

  • Get Trip

    Tool to retrieve a trip by id or externalid. use when you have a trip id or externalid to fetch its details.

  • Get Users in Geofence

    Tool to retrieve users currently within a specific geofence. use when you need to list all users inside a geofence by its tag and external id.

  • IP Geocode

    Tool to geocode an ip address to city, state, and country. use when you need location details based on an ip address.

  • List Beacons

    Tool to list all beacons sorted by creation date. use when you need an overview of all configured beacons.

  • List Events

    Tool to list events. use when you need to retrieve a paginated list of events with optional filtering.

  • List Geofences

    Tool to list all geofences sorted by updated time. use when you need an overview of all configured geofences.

  • List Trips

    Tool to list all trips, sorted by updated time. use when you need to page through the latest trips.

  • List Users

    Tool to list radar users sorted by update time. use when you need to page through users in your project.

  • Reverse Geocode

    Tool to convert geographic coordinates to structured addresses. use when you have latitude/longitude and need a human-readable address.

  • Route Distance

    Tool to compute distance and travel time between origins and destinations. use when you need route metrics before optimizing or timing routes.

  • Search Geofences

    Tool to search for geofences near a given location. use when you need to find geofences within a radius of specified coordinates.

  • Search Places Near Location

    Tool to search for places near given coordinates. use when you need to find points of interest around a location.

  • Search Users Near Location

    Tool to search for users near a location. use after obtaining coordinates when you need to retrieve users within a given radius.

  • Track Location Update

    Tool to track a user's location update. use when sending a location update for a user, creating or updating user and event data.

  • Update Trip

    Tool to update a trip. use when you need to modify mode, destination, schedule, or active status.

  • Upsert Geofence

    Tool to create or update a geofence by tag and externalid. use when ensuring a geofence exists or is updated based on identifiers.

Setup

Setup guide

  1. 11. Open your Switchy workspace settings and navigate to the Integrations tab. 2. Click 'Add MCP Integration' and select Radar from the developer tools category. 3. Log into your Radar account at radar.com, go to Settings > API Keys, and copy your publishable or secret key (secret key recommended for server-side operations). 4. Paste the API key into Switchy's connection dialog and click Connect. 5. Switchy confirms the connection by fetching your Places settings — you'll see a success message if the key is valid. 6. Open any Space, type '@Radar' in the chat, and ask it to forward geocode an address or autocomplete a partial place name to verify the integration works.

What teammates see: by default, memories from Radar are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.

Works well with

Top models

Compatibility data appears once enough Spaces have used this MCP together with a given model.

How Switchy teams use it

Not enough Spaces yet to publish anonymised usage stats (we require ≥ 50 Spaces per week).

Starter prompts

Geocode Address

@Radar forward geocode the address '1600 Amphitheatre Parkway, Mountain View, CA 94043' and return the coordinates.
Open in a Space →

Autocomplete Place

@Radar autocomplete the partial input 'Golden Gate' near San Francisco and show the top five suggestions.
Open in a Space →

Get Location Context

@Radar get context for latitude 37.7749 and longitude -122.4194, including any geofences and nearby places.
Open in a Space →

Create Delivery Trip

@Radar create a trip from '123 Main St, Austin, TX' to '456 Oak Ave, Austin, TX' with external ID 'delivery-5678'.
Open in a Space →

Inspect Geofence

@Radar get the geofence with tag 'downtown-zone' and show its geometry and metadata.
Open in a Space →

Example outputs

Illustrative - representative of the model's voice and quality, not literal recordings.

Prompt

@Radar what geofences and places are near 37.7749, -122.4194? I need context for this location to understand what's around our SF office.

Output

Based on the coordinates 37.7749, -122.4194 (San Francisco), this location falls within 2 active geofences: 'downtown-sf-zone' (radius 500m) and 'market-street-corridor' (polygon boundary). Nearby places include Civic Center Plaza (0.3km), UN Plaza (0.4km), and several transit stations. The region context shows this is in San Francisco County, California, US, postal code 94102. This data reflects your account's current geofence configuration and Radar's place database as of this query.

Notes

This example shows Radar's core location intelligence — combining your custom geofences with Radar's place data. Requires valid lat/long input and an API key with geofence read permissions. The geofences returned depend entirely on what you've previously created in your Radar project; this is illustrative output.

Prompt

@Radar create a trip from 123 Main St, Austin TX to 456 Oak Ave, Dallas TX with external ID 'delivery-order-7821' so we can track this route in real-time.

Output

Trip created successfully with Radar ID `trip_abc123xyz`. Origin geocoded to 30.2672, -97.7431 (Austin) and destination to 32.7767, -96.7970 (Dallas). External ID 'delivery-order-7821' attached for your reference. The trip is now live and will generate location updates as the device moves along the route. Estimated distance: 195 miles. You can query trip status or delete it using the Radar ID or your external ID.

Notes

This demonstrates Radar's trip tracking workflow — geocoding addresses, creating the trip object, and returning identifiers for ongoing monitoring. Requires API key with trip write permissions. The trip persists in Radar's system until explicitly deleted or completed; be mindful of active trip quotas on your plan.

Prompt

@Radar I'm typing '1600 Pennsylv' — autocomplete this address and tell me the top 3 suggestions so I can pick the right one for our DC event venue search.

Output

Top 3 autocomplete suggestions for '1600 Pennsylv': (1) 1600 Pennsylvania Avenue NW, Washington, DC 20500 (The White House), (2) 1600 Pennsylvania Avenue SE, Washington, DC 20003 (residential area), (3) 1600 Pennsylvania Street, Denver, CO 80203. Each result includes full formatted address and coordinates. The ranking prioritizes relevance and proximity if you pass a bias location. This is a partial match query — results improve as the user types more characters.

Notes

Showcases Radar's autocomplete for address entry UX — useful in forms or search interfaces where users type incrementally. Requires API key with geocoding permissions. Autocomplete is rate-limited (check your plan); results vary by query specificity and optional location bias. This example illustrates typical output structure, not a live query.

Use-case deep-dives

Field service dispatch routing

When Radar wins for same-day service territory checks

A 6-person HVAC dispatch team runs 15-20 calls a day across three metro zones. They need to know if a new service request falls inside their coverage geofences and which tech is closest. Radar's Get Context for Location and geofence tools answer both questions in one call—no manual map checking, no spreadsheet lookups. The team creates geofences for each territory, then uses Forward Geocode to turn customer addresses into coordinates and Get Context to match them to zones and nearby techs. This works cleanly when your service area has stable boundaries and you're making under 10k lookups a month. If your zones shift weekly or you're routing 50+ techs, you'll hit the API rate limit and need a heavier GIS stack. For small field teams with fixed territories, Radar keeps dispatch decisions fast and removes the guesswork.

Delivery app order handoff

When trip tracking fits courier handoff workflows

A 3-person logistics startup coordinates handoffs between warehouse packers and gig couriers for same-day grocery delivery. They need to know when a courier arrives at the warehouse and when they leave for the customer. Radar's Create Trip and trip lifecycle tools let them track each leg without building GPS polling from scratch. The warehouse app calls Create Trip when a courier accepts an order, Radar pings the backend when the courier enters the pickup geofence, and the customer gets an ETA update when the trip starts moving toward delivery. This setup works when you're doing under 500 deliveries a day and your couriers use a single app. If you're coordinating multi-modal handoffs or need sub-minute location updates, Radar's trip abstraction gets too coarse. For early-stage delivery ops with straightforward pickup-to-dropoff flows, it's the fastest way to add live tracking without a geospatial engineering hire.

Retail store locator autocomplete

When Radar's autocomplete beats rolling your own

A 10-store regional retail chain wants a store locator on their site that suggests locations as customers type. They need autocomplete that biases results toward their operating region and doesn't send users to competitors. Radar's Autocomplete Address or Place tool returns ranked suggestions with proximity bias, so a customer typing 'Main St' in Portland sees the Portland store first, not the one in Seattle. The team wires it to their storefront search bar and uses Forward Geocode to snap the final selection to coordinates for distance sorting. This works when you have under 50 locations and your customers are searching within a known region. If you're a national chain with 500+ stores or need to filter by real-time inventory, you'll want a full Places API with custom ranking. For regional retailers who need fast, relevant autocomplete without maintaining a geocoding pipeline, Radar's tooling is the right scope.

Frequently asked

What does the Radar MCP let me do in Switchy?

It gives your AI agents access to Radar's location APIs — geocoding addresses, creating geofences, tracking trips, and pulling contextual data about coordinates. You can automate location workflows without writing code, like converting customer addresses to lat/long or checking which geofences a delivery driver entered.

Do I need a paid Radar account to use this MCP?

Yes. You need a Radar API key, which requires a Radar account. Radar offers a free tier with limited requests per month. The MCP uses your key to authenticate every call, so usage counts against your Radar plan limits — not Switchy's.

Can the Radar MCP create or update places in my Radar project?

No. The MCP reads places settings and retrieves place context for coordinates, but it doesn't create or modify places. If you need to manage your places catalog, use Radar's dashboard or their Places API directly. The MCP focuses on geocoding, geofences, and trip tracking.

How is this different from calling Radar's API myself?

The MCP wraps Radar's REST API so your AI agents can call it conversationally — no curl commands or JSON parsing. You describe what you want in plain English; the agent picks the right tool and parameters. For one-off scripts or custom integrations, the API is faster. For agent workflows, the MCP is simpler.

Who on my team should connect the Radar MCP?

Whoever owns your Radar account and can generate API keys. That's usually a developer or ops lead. Once connected in Switchy, any team member with workspace access can use the MCP in their agent chats — they don't need their own Radar credentials.

Data last verified 607 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.