Lusha for AI agents
Lusha is a B2B contact enrichment platform that provides verified phone numbers, emails, and company information for prospecting and recruiting teams. 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 Lusha.
Check a subscription's usage
Look up a subscription's contact reveal usage before running a large enrichment batch, read-only.
Review enrichment audit logs
Pull audit log stats to see recent contact lookups made under an account.
Approve before deleting a subscription
Require approval before deleting a subscription, since it changes billing and access.
7 Lusha actions, graded by risk.
Every Lusha action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- lusha.get_audit_logsGet Audit Logs
- lusha.get_subscriptionGet Subscription
- lusha.list_subscriptionsList Subscriptions
- lusha.get_audit_log_statsGet Audit Log Stats
write
2Create and change things. Allow, or ask the user first.
- lusha.create_subscriptionCreate Subscription
- lusha.update_subscriptionUpdate Subscription
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- lusha.delete_subscriptionsDelete Subscriptions
Lusha in three steps.
- 01Your users connect LushaThey add their Lusha api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Subscription” can wait for the user, and “delete Subscriptions” can be denied outright.
- 03Any agent can actYour agent calls Lusha through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('lusha', { read: 'allow', write: 'ask', // create_subscription destructive: 'deny', // delete_subscriptions }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Lusha connects.
Users add their Lusha 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 Lusha 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 Lusha from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Lusha and Arc0, answered.
Can I use Lusha with Claude, ChatGPT or Cursor?
Yes. Connect Lusha 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 Lusha actions you allow.
How do users connect Lusha?
Users add their Lusha 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 Lusha actions can my agent take?
7 in total: 4 read, 2 write and 1 destructive, such as “create Subscription”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Lusha?
Yes. Actions like “delete Subscriptions” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Lusha too?
Yes. The same Lusha connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Lusha into your agent.
Your users connect Lusha once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan