Harp, the MCP harness for pipeline generation

What Harp gives your AI agent: LinkedIn at human pace, replies answered within minutes, email that lands, research that persists, and an MCP server built for long account lists.

• LinkedIn automation that runs from your own Mac

  Harp runs LinkedIn steps from your real Chrome on your own Mac, at the operating-system level: click navigation, human timing, daily limits, a four-week warm-up and a right-person check before every message or invite.

• Replies answered within minutes

  When a prospect replies, Harp stops the sequence and wakes your AI agent, which answers the email and books the meeting on your calendar within minutes during your working hours. LinkedIn replies wait for your yes in Slack.

• Email sequences that land

  Harp sends cold email from your own Google Workspace mailbox with a 28-day warm-up, 2 to 6 minutes between sends, delivery in the recipient’s working hours, plain-text copies, tracking off by default and one-click unsubscribe.

• Research that persists

  Harp stores your AI agent’s research as answers to your qualification questions, each with evidence, source and age, so the agent refreshes only what is stale and every first line has something true to say.

• An MCP server built for agents

  Harp’s MCP server gives your AI agent a short list of daily outbound tools, folders for everything else and compact results, so whole account lists fit in its context.