> ## Documentation Index
> Fetch the complete documentation index at: https://docs.harpgtm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Common questions about Harp: running outbound from Claude, AI credits, LinkedIn account safety, reply handling, email sending and pricing.

## What is Harp?

Harp (harpgtm.com) is the MCP harness for pipeline generation. Your own AI agent does the research, writing and decisions through Harp's MCP tools. Harp holds the accounts, contacts, sequences and history, and does the sending across email and LinkedIn.

## Who is Harp for?

Founders, account executives and GTM engineers who already use an AI agent as their sales development rep and want a proper place for that work to live, instead of spreadsheets, CRM tasks and copy-paste.

## How do I run outbound from Claude?

Connect Harp's MCP server to Claude Code, Claude Desktop or Cowork. Claude starts each session with a briefing, finds and qualifies accounts, saves research with evidence, and enrolls contacts in sequences. Harp sends the emails from your mailbox and queues the LinkedIn steps. See [Run outbound from Claude](https://docs.harpgtm.com/guides/claude-mcp.md).

## Does Harp work with ChatGPT or other AI agents?

Harp's tools speak MCP, the open standard AI agents use to connect to tools. Today Harp is set up with Claude: Claude Code, Claude Desktop or Cowork. If your team runs on a different agent, [talk to us](mailto:sales@harpgtm.com).

## Do I need to buy AI credits?

No. You bring your own AI plan. Harp does not sell AI credits and does not run its own model on your outreach.

## How does Harp keep a LinkedIn account safe?

Harp drives your real Chrome on a Mac at the operating-system level, moving the mouse and typing the way a person does. There is no browser extension, no injected code, no LinkedIn API and no headless browser, so there is nothing extra in the browser for LinkedIn to detect.

It moves around LinkedIn by clicking, the way a person browses, instead of jumping straight to profile URLs. Timing varies like a person's, every action type has a daily limit that varies day to day, and new accounts start on a four-week warm-up. Before it sends a message or connection request, it checks it is on the right person's profile, and if it cannot confirm that, it does not send.

No tool can guarantee LinkedIn will never restrict an account. Harp is built to keep activity at human volumes and patterns. See [LinkedIn automation](https://docs.harpgtm.com/guides/linkedin-automation.md).

## Does LinkedIn automation work on Windows?

Not yet. LinkedIn automation needs a Mac with Chrome.

## How are replies handled?

Within minutes during working hours. Claude answers email replies, books meetings and pauses or stops sequences. LinkedIn replies wait for a yes from you in Slack before anything is sent. See [Reply handling](https://docs.harpgtm.com/guides/reply-handling.md).

## Where does email get sent from?

From your own Google Workspace mailbox, not shared sending servers. Each mailbox has a daily limit, sends are spaced a few minutes apart, and emails land in the recipient's local working hours when their timezone is known. A reply, bounce or unsubscribe stops that person's sequence automatically.

## How much does Harp cost?

Harp is a flat subscription with no AI credits. There is no public price list: the Harp team sets up every customer after a short call. Email [sales@harpgtm.com](mailto:sales@harpgtm.com).

## Is there a free trial?

No. Harp is set up with every customer by the Harp team, so there is no self-serve trial.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.