Fullenrich for AI agents
FullEnrich aggregates data from over 15 vendors to find verified emails and phone numbers for B2B sales leads, used by sales development teams building 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 Fullenrich.
Start a bulk enrichment job
Start bulk enrichment on a list of leads to fill in verified emails and phone numbers.
Check an enrichment job's results
Get the results of a bulk enrichment job once processing finishes.
Check credit balance before a batch
Read the credit balance before starting a large enrichment job across many contacts.
9 Fullenrich actions, graded by risk.
Every Fullenrich 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.
- fullenrich.search_peopleSearch People
- fullenrich.search_companySearch Company
- fullenrich.get_enrichment_resultGet Bulk Enrichment Result
- fullenrich.get_reverse_email_resultGet Reverse Email Result
- fullenrich.get_current_credit_balanceGet current credit balance
- fullenrich.verify_api_keyVerify API Key
write
3Create and change things. Allow, or ask the user first.
- fullenrich.create_contact_data_listCreate Contact Data List
- fullenrich.reverse_email_lookupReverse Email Lookup
- fullenrich.start_bulk_enrichmentStart Bulk Enrichment
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Fullenrich in three steps.
- 01Your users connect FullenrichThey add their Fullenrich api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Contact Data List” can wait for the user to approve.
- 03Any agent can actYour agent calls Fullenrich through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('fullenrich', { read: 'allow', write: 'ask', // create_contact_data_list destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Fullenrich connects.
Users add their Fullenrich 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 Fullenrich 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 Fullenrich from any agent.
Fullenrich and Arc0, answered.
Can I use Fullenrich with Claude, ChatGPT or Cursor?
Yes. Connect Fullenrich 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 Fullenrich actions you allow.
How do users connect Fullenrich?
Users add their Fullenrich 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 Fullenrich actions can my agent take?
9 in total: 6 read, 3 write and 0 destructive, such as “create Contact Data List”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Fullenrich?
Yes. Allow read actions and deny writes in the Fullenrich policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Fullenrich too?
Yes. The same Fullenrich connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Fullenrich into your agent.
Your users connect Fullenrich once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan