LeadBoxer for AI agents
LeadBoxer identifies the companies and people visiting a website and turns that anonymous traffic into scored, actionable leads for a sales team to follow up on. 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 LeadBoxer.
Look up a lead's detail
Pull the full profile and score for a lead identified from website visits.
Tag a lead for follow-up
Add a tag to a lead record so sales knows to prioritize it.
Check recent site sessions
List recent visitor sessions to spot a company worth a follow-up, read-only.
9 LeadBoxer actions, graded by risk.
Every LeadBoxer 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.
- leadboxer.get_eventsGet Events
- leadboxer.get_sessionsGet Sessions
- leadboxer.get_lead_score_formulaGet Lead Score Formula
write
5Create and change things. Allow, or ask the user first.
- leadboxer.post_eventPost Event Data
- leadboxer.add_or_update_lead_tagsAdd or Update Lead Tags
- leadboxer.log_eventLog Server-Side Event
- leadboxer.management_ctdGet Custom Tracking Domains
- leadboxer.views_lead_detailGet Lead Detail
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- leadboxer.delete_ctdDelete Custom Tracking Domain
LeadBoxer in three steps.
- 01Your users connect LeadBoxerThey add their LeadBoxer api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “add or Update Lead Tags” can wait for the user, and “delete Custom Tracking Domain” can be denied outright.
- 03Any agent can actYour agent calls LeadBoxer through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('leadboxer', { read: 'allow', write: 'ask', // add_or_update_lead_tags destructive: 'deny', // delete_ctd }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How LeadBoxer connects.
Users add their LeadBoxer 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 LeadBoxer 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 LeadBoxer from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
LeadBoxer and Arc0, answered.
Can I use LeadBoxer with Claude, ChatGPT or Cursor?
Yes. Connect LeadBoxer 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 LeadBoxer actions you allow.
How do users connect LeadBoxer?
Users add their LeadBoxer 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 LeadBoxer actions can my agent take?
9 in total: 3 read, 5 write and 1 destructive, such as “add or Update Lead Tags”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in LeadBoxer?
Yes. Actions like “delete Custom Tracking Domain” 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 LeadBoxer too?
Yes. The same LeadBoxer connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug LeadBoxer into your agent.
Your users connect LeadBoxer 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