Get started

Opencage for AI agents

OpenCage Geocoder converts addresses into coordinates and coordinates back into addresses using open geographic data. Developers use it to add location lookup to applications. 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.

Connect OpencageSee the 7 actions ↓
Developer toolsAPI keyMCP + RESTopencagedata.com
AUDIT LOG · OPENCAGEPOLICY: acme-support
09:41:07 · claude · u_8f2read
opencage.ping_opencage
Check API Health✓ allowed · 212ms
09:41:09 · claude · u_8f2write
opencage.geocode_xml
Geocode XML✓ approved · approved by user
EVERY OPENCAGE CALL, ON THE RECORD
01 · USE CASES

What agents do in Opencage.

01

Geocode an address to coordinates

Convert a customer's street address into latitude and longitude for mapping.

02

Reverse geocode a location

Look up the nearest address for a set of coordinates captured from a device.

03

Check API health read-only

Confirm the geocoding service is responsive before relying on it in a live workflow.

02 · ACTIONS

7 Opencage actions, graded by risk.

Every Opencage action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

1

Look things up. Allowed by default.

  • opencage.ping_opencage
    Check API Health

write

6

Create and change things. Allow, or ask the user first.

  • opencage.geocode_xml
    Geocode XML
  • opencage.geocode_forward
    Forward Geocode Address
  • opencage.geocode_geojson
    Geocode to GeoJSON
  • opencage.geocode_reverse
    Reverse Geocode Coordinates
  • opencage.geocode_geojsonp
    Geocode with JSONP
  • opencage.geocode_google_v3_json
    Geocode Google v3 JSON

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Opencage in three steps.

  1. 01Your users connect OpencageThey add their Opencage api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “geocode XML” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Opencage through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('opencage', {
  read: 'allow',
  write: 'ask',        // geocode_xml
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Opencage connects.

Users add their Opencage 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 Opencage 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
05 · WORKS WITH

Use Opencage from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Opencage and Arc0, answered.

Q01

Can I use Opencage with Claude, ChatGPT or Cursor?

Yes. Connect Opencage 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 Opencage actions you allow.

Q02

How do users connect Opencage?

Users add their Opencage 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.

Q03

Which Opencage actions can my agent take?

7 in total: 1 read, 6 write and 0 destructive, such as “geocode XML”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Opencage?

Yes. Allow read actions and deny writes in the Opencage policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Opencage too?

Yes. The same Opencage connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Opencage into your agent.

Your users connect Opencage once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.

Connect OpencageBrowse all apps →

Free to build · MCP + REST · Audit log on every plan