Radar for AI agents
Radar is a location infrastructure platform offering geofencing, tracking, geocoding, and routing through one API. Product teams use it to add location-aware features to apps. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Radar.
Geocode an address
Convert a customer address into coordinates to plot on a delivery map.
Check users in a geofence read-only
List users currently inside a geofence without sending any notification.
Delete a geofence with approval
Remove a geofence only after confirming it is no longer part of an active campaign.
37 Radar actions, graded by risk.
Every Radar action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
18Look things up. Allowed by default.
- radar.get_tripGet Trip
- radar.get_userGet User
- radar.get_beaconGet Beacon
- radar.list_tripsList Trips
- radar.list_usersList Users
- radar.list_eventsList Events
- radar.get_geofenceGet Geofence
- radar.list_geofencesList Geofences
- radar.get_route_matrixGet Route Matrix
- radar.get_beacon_by_tagGet Beacon By Tag
- radar.get_places_settingsGet Places Settings
- radar.get_route_directionsGet Route Directions
- radar.get_users_in_geofenceGet Users in Geofence
- radar.get_context_for_locationGet Context for Location
- radar.search_users_near_locationSearch Users Near Location
- radar.search_places_near_locationSearch Places Near Location
write
14Create and change things. Allow, or ask the user first.
- radar.create_tripCreate Trip
- radar.update_tripUpdate Trip
- radar.create_beaconCreate Beacon
- radar.update_trip_by_idUpdate Trip By ID
- radar.update_places_settingsUpdate Places Settings
- radar.ip_geocodeIP Geocode
- radar.route_distanceRoute Distance
- radar.forward_geocodeForward Geocode
- radar.reverse_geocodeReverse Geocode
- radar.upsert_geofenceUpsert Geofence
- radar.upsert_beacon_by_idUpsert Beacon by ID
- radar.upsert_beacon_by_tagUpsert Beacon by Tag
- radar.upsert_geofence_by_idUpsert Geofence By ID
- radar.autocomplete_address_or_placeAutocomplete Address or Place
destructive
5Delete, cancel or archive. Ask first, or deny outright.
- radar.delete_tripDelete Trip
- radar.delete_userDelete User
- radar.delete_beaconDelete Beacon
- radar.delete_geofenceDelete Geofence
- radar.delete_geofence_by_tagDelete Geofence By Tag
Radar in three steps.
- 01Your users connect RadarThey add their Radar api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Trip” can wait for the user, and “delete Trip” can be denied outright.
- 03Any agent can actYour agent calls Radar through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('radar', { read: 'allow', write: 'ask', // create_trip destructive: 'deny', // delete_trip }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Radar connects.
Users add their Radar api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Radar connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Radar from any agent.
Radar and Arc0, answered.
Can I use Radar with Claude, ChatGPT or Cursor?
Yes. Connect Radar to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Radar actions you allow.
How do users connect Radar?
Users add their Radar api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Radar actions can my agent take?
37 in total: 18 read, 14 write and 5 destructive, such as “create Trip”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Radar?
Yes. Actions like “delete Trip” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Radar too?
Yes. The same Radar connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Radar into your agent.
Your users connect Radar once, under your brand. Your agent gets 37 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan