Explorium for AI agents
Explorium AgentSource provides company and prospect discovery and enrichment, helping sales teams find and research target accounts before launching an outbound campaign. 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 Explorium.
Search for target businesses
Search businesses matching a target profile to build a prospecting list for a campaign.
Enrich a company's firmographics
Enrich a business record with firmographic data before it is added to a CRM.
Check credit balance first
Read the credit balance before running a large batch of prospect matching.
10 Explorium actions, graded by risk.
Every Explorium 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.
- explorium.list_jobsList Jobs
- explorium.get_job_statusGet Job Status
- explorium.search_prospectsSearch Prospects
- explorium.search_businessesSearch Businesses
- explorium.get_audience_statsGet Audience Stats
- explorium.get_credit_balanceGet Credit Balance
write
4Create and change things. Allow, or ask the user first.
- explorium.match_prospectsMatch Prospects
- explorium.match_businessesMatch Businesses
- explorium.autocomplete_filter_valuesAutocomplete Filter Values
- explorium.enrich_business_firmographicsEnrich Business Firmographics
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Explorium in three steps.
- 01Your users connect ExploriumThey add their Explorium api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “match Prospects” can wait for the user to approve.
- 03Any agent can actYour agent calls Explorium through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('explorium', { read: 'allow', write: 'ask', // match_prospects destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Explorium connects.
Users add their Explorium 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 Explorium 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 Explorium from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Explorium and Arc0, answered.
Can I use Explorium with Claude, ChatGPT or Cursor?
Yes. Connect Explorium 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 Explorium actions you allow.
How do users connect Explorium?
Users add their Explorium 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 Explorium actions can my agent take?
10 in total: 6 read, 4 write and 0 destructive, such as “match Prospects”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Explorium?
Yes. Allow read actions and deny writes in the Explorium policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Explorium too?
Yes. The same Explorium connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Explorium into your agent.
Your users connect Explorium 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