Ocean.io for AI agents
Ocean.io provides go-to-market intelligence for finding and enriching companies and people that match a target customer profile. Sales and marketing teams use it to build and qualify prospect lists. 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 Ocean.io.
Search companies by ideal profile
Find companies matching a target industry and size to seed a new outbound list.
Enrich a prospect record
Pull firmographic details for a company or person before adding them to a CRM record.
Check remaining credit balance
Look up the account's credit balance read-only before running a large enrichment batch.
10 Ocean.io actions, graded by risk.
Every Ocean.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- ocean_io.search_peopleSearch People
- ocean_io.search_companiesSearch Companies
- ocean_io.get_credit_balanceGet Credit Balance
- ocean_io.get_data_field_valuesGet Data Field Values
- ocean_io.lookup_peopleLookup People
- ocean_io.lookup_companiesLookup Companies
write
4Create and change things. Allow, or ask the user first.
- ocean_io.enrich_personEnrich Person
- ocean_io.enrich_companyEnrich Company
- ocean_io.autocomplete_valuesAutocomplete Values
- ocean_io.gather_missing_company_dataGather Missing Company Data
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Ocean.io in three steps.
- 01Your users connect Ocean.ioThey add their Ocean.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “enrich Person” can wait for the user to approve.
- 03Any agent can actYour agent calls Ocean.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ocean_io', { read: 'allow', write: 'ask', // enrich_person destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ocean.io connects.
Users add their Ocean.io 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 Ocean.io 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 Ocean.io from any agent.
Ocean.io and Arc0, answered.
Can I use Ocean.io with Claude, ChatGPT or Cursor?
Yes. Connect Ocean.io 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 Ocean.io actions you allow.
How do users connect Ocean.io?
Users add their Ocean.io 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 Ocean.io actions can my agent take?
10 in total: 6 read, 4 write and 0 destructive, such as “enrich Person”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Ocean.io?
Yes. Allow read actions and deny writes in the Ocean.io policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Ocean.io too?
Yes. The same Ocean.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ocean.io into your agent.
Your users connect Ocean.io once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan