Bettercontact for AI agents
Bettercontact finds verified email addresses and phone numbers for a list of leads using a waterfall of data sources, used by sales and growth teams for contact enrichment. 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 Bettercontact.
Check enrichment credit balance
Check the remaining credit balance before running a large enrichment job so it doesn't fail partway through.
Enrich a list of leads
Submit a list of leads to find verified emails and phone numbers before handing them to a sales rep.
Pull results from a finder search
Get the results of a lead finder search once processing completes, a read-only check on an async job.
5 Bettercontact actions, graded by risk.
Every Bettercontact action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- bettercontact.get_enrichment_resultsGet Enrichment Results
- bettercontact.get_lead_finder_resultsGet Lead Finder Results
- bettercontact.check_credits_balanceCheck Credits Balance
write
2Create and change things. Allow, or ask the user first.
- bettercontact.create_lead_finder_searchCreate Lead Finder Search
- bettercontact.enrich_leadsEnrich Leads
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Bettercontact in three steps.
- 01Your users connect BettercontactThey add their Bettercontact api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Lead Finder Search” can wait for the user to approve.
- 03Any agent can actYour agent calls Bettercontact through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('bettercontact', { read: 'allow', write: 'ask', // create_lead_finder_search destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Bettercontact connects.
Users add their Bettercontact 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 Bettercontact 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 Bettercontact from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Bettercontact and Arc0, answered.
Can I use Bettercontact with Claude, ChatGPT or Cursor?
Yes. Connect Bettercontact 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 Bettercontact actions you allow.
How do users connect Bettercontact?
Users add their Bettercontact 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 Bettercontact actions can my agent take?
5 in total: 3 read, 2 write and 0 destructive, such as “create Lead Finder Search”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Bettercontact?
Yes. Allow read actions and deny writes in the Bettercontact policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Bettercontact too?
Yes. The same Bettercontact connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Bettercontact into your agent.
Your users connect Bettercontact once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan