Wiza for AI agents
Wiza finds and exports verified contact data for LinkedIn prospects, used by sales teams building outbound lists with working emails and phone numbers. 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 Wiza.
Search prospects on LinkedIn
Find prospects matching a role and company filter, a read-only search.
Start an individual reveal
Request contact details for a specific prospect found through search.
Check remaining credits
Read remaining API credits before running a large prospect search.
5 Wiza actions, graded by risk.
Every Wiza 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.
- wiza.get_listGet List Details
- wiza.get_creditsGet API Credits
- wiza.get_individual_revealGet Individual Reveal
write
2Create and change things. Allow, or ask the user first.
- wiza.prospect_searchSearch Prospects
- wiza.start_individual_revealStart Individual Reveal
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Wiza in three steps.
- 01Your users connect WizaThey add their Wiza api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “search Prospects” can wait for the user to approve.
- 03Any agent can actYour agent calls Wiza through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('wiza', { read: 'allow', write: 'ask', // prospect_search destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Wiza connects.
Users add their Wiza 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 Wiza 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 Wiza from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Wiza and Arc0, answered.
Can I use Wiza with Claude, ChatGPT or Cursor?
Yes. Connect Wiza 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 Wiza actions you allow.
How do users connect Wiza?
Users add their Wiza 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 Wiza actions can my agent take?
5 in total: 3 read, 2 write and 0 destructive, such as “search Prospects”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Wiza?
Yes. Allow read actions and deny writes in the Wiza policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Wiza too?
Yes. The same Wiza connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Wiza into your agent.
Your users connect Wiza 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