Ipdata.co for AI agents
ipdata.co is a simple HTTP API for looking up the location, ownership, and threat profile of any IP address. Developers wire it into their own apps and internal tools instead of building the underlying capability from scratch. 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 Ipdata.co.
Look up a city from an IP
Look up the city behind a visitor's IP address to localize a welcome message.
Check a threat score for an IP
Check an IP's threat score before allowing a high-risk action like a password reset.
Bulk lookup a list of IPs
Run a bulk lookup on a list of IPs pulled from server logs for a traffic report.
28 Ipdata.co actions, graded by risk.
Every Ipdata.co action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
28Create and change things. Allow, or ask the user first.
- ipdata_co.field_ipIPData: IP
- ipdata_co.field_cityGet City from IP
- ipdata_co.field_countIPDATA Field Count
- ipdata_co.field_is_euIPData: Is EU
- ipdata_co.field_postalIPData: Postal Code
- ipdata_co.field_regionGet Region from IP
- ipdata_co.field_threatGet Threat for IP
- ipdata_co.field_carrierIPDATA Field Carrier
- ipdata_co.field_currencyIPDATA Field Currency
- ipdata_co.field_latitudeIPData: Latitude
- ipdata_co.field_languagesIPData: Languages
- ipdata_co.field_longitudeGet Longitude from IP
- ipdata_co.field_time_zoneIPData: Time Zone
- ipdata_co.field_emoji_flagGet Emoji Flag from IP
- ipdata_co.field_region_codeIPData: Region Code
- ipdata_co.field_calling_codeIPData: Calling Code
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Ipdata.co in three steps.
- 01Your users connect Ipdata.coThey add their Ipdata.co api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “iPData: IP” can wait for the user to approve.
- 03Any agent can actYour agent calls Ipdata.co through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ipdata_co', { read: 'allow', write: 'ask', // field_ip destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ipdata.co connects.
Users add their Ipdata.co 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 Ipdata.co 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 Ipdata.co from any agent.
Ipdata.co and Arc0, answered.
Can I use Ipdata.co with Claude, ChatGPT or Cursor?
Yes. Connect Ipdata.co 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 Ipdata.co actions you allow.
How do users connect Ipdata.co?
Users add their Ipdata.co 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 Ipdata.co actions can my agent take?
28 in total: 0 read, 28 write and 0 destructive, such as “iPData: IP”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Ipdata.co?
Yes. Allow read actions and deny writes in the Ipdata.co policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Ipdata.co too?
Yes. The same Ipdata.co connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ipdata.co into your agent.
Your users connect Ipdata.co once, under your brand. Your agent gets 28 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan