Leadfeeder for AI agents
Leadfeeder identifies the companies visiting a website by matching IP addresses to firmographic data, surfacing them as sales leads worth a follow-up call. 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 Leadfeeder.
Look up a visitor's company
Resolve an IP address to a company name and details for a visit worth following up on.
Check recent website visits
List recent visits across accounts to find companies that browsed a pricing page.
Pull visit history, read-only
Read a specific account's visit history before a sales rep reaches out, a read-only lookup that changes nothing.
6 Leadfeeder actions, graded by risk.
Every Leadfeeder 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.
- leadfeeder.get_accountGet Account
- leadfeeder.get_accountsGet Accounts
- leadfeeder.get_all_visitsGet All Visits
- leadfeeder.get_custom_feedsGet Custom Feeds
- leadfeeder.get_tracking_scriptGet Tracking Script
- leadfeeder.get_company_info_by_ipGet Company Info by IP
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Leadfeeder in three steps.
- 01Your users connect LeadfeederThey add their Leadfeeder api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Leadfeeder through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('leadfeeder', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Leadfeeder connects.
Users add their Leadfeeder 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 Leadfeeder 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 Leadfeeder from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Leadfeeder and Arc0, answered.
Can I use Leadfeeder with Claude, ChatGPT or Cursor?
Yes. Connect Leadfeeder 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 Leadfeeder actions you allow.
How do users connect Leadfeeder?
Users add their Leadfeeder 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 Leadfeeder actions can my agent take?
6 in total: 6 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Leadfeeder?
Yes. Allow read actions and deny writes in the Leadfeeder policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Leadfeeder too?
Yes. The same Leadfeeder connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Leadfeeder into your agent.
Your users connect Leadfeeder once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan