# Everything BounceHound does to keep your emails from bouncing

> A tour of BounceHound: the checks it runs on every address, the five result statuses, four ways to verify, pay-as-you-go credits, and connecting it to your AI agent with MCP.

The BounceHound team · 2026-10-13 · https://bouncehound.com/blog/bouncehound-features

Every bounced email chips away at your sender reputation. Send to enough dead addresses and inbox providers start routing even your good mail to spam. BounceHound exists to stop that before you hit send: it checks each address and tells you, in plain terms, whether it's safe to mail.

This post walks through what BounceHound actually does with every address, how credits work, and the feature we're most excited about: connecting it straight to your AI agent.

## What happens when you verify an address

BounceHound runs the cheapest, fastest checks first and only spends a credit when it has to.

1. **Syntax check.** Malformed addresses like `jane@@acme` or `bob@gmail` are flagged as invalid immediately.
2. **Typo suggestions.** Common slips like `gmial.com`, `hotmial.com` or `yahoo.con` come back with a "did you mean" fix, so you can correct the address instead of losing the lead.
3. **Disposable detection.** Throwaway inbox domains (Mailinator and friends) are flagged as disposable. They're rarely real leads.
4. **Role and free-provider flags.** Addresses like `info@`, `support@` or `sales@` are marked as role accounts, and Gmail, Outlook, Yahoo and similar are marked as free providers, so you can segment them.
5. **MX lookup.** If the domain has no mail server at all, the address can't receive email and is marked invalid.
6. **Mailbox check.** Only the addresses that pass all of the above go on to a mailbox-level check, which asks the recipient's mail server whether the mailbox exists. No email is ever sent to the address.

Steps 1 to 5 are free. You only use a credit on step 6.

## Five clear answers

Every address comes back with one status you can act on:

| Status | What it means | What to do |
|---|---|---|
| **Valid** | The mailbox exists | Safe to send |
| **Invalid** | Bad syntax, no mail server, or the mailbox was rejected | Remove it |
| **Risky** | The domain accepts every address (catch-all), so the mailbox can't be confirmed | Send with care |
| **Disposable** | A throwaway inbox | Usually not a real lead |
| **Unknown** | The mail server didn't answer | Retry later. Never charged |

Each result also includes the reason, the mail server it checked, and the role, free-provider and disposable flags.

## Four ways to verify

- **Upload a list.** Drop in a CSV, TXT or XLSX file. BounceHound scans every column for addresses and removes duplicates before you're charged.
- **Paste emails.** Paste a handful of addresses straight into the dashboard.
- **Call the API.** One REST request verifies an address at signup or inside your data pipeline. A bulk endpoint handles up to 10,000 addresses per request.
- **Ask your AI agent.** More on this below.

When a list finishes, download the results as CSV: everything, valid only, or valid plus risky.

## Plug it into your AI agent

This is what makes BounceHound different. It includes a built-in **MCP server**, the open standard AI assistants use to call tools. Connect it once and your agent can verify and clean email lists on its own.

In Claude Code, it's one command:

```bash
claude mcp add --transport http bouncehound https://bouncehound.com/api/mcp \
  --header "Authorization: Bearer YOUR_KEY"
```

Cursor, Claude Desktop, VS Code, Windsurf, ChatGPT and n8n are supported too, and the dashboard gives you a copy-paste setup for each.

Then just ask:

- "Verify `jane@acme.com`"
- "Clean the emails in leads.csv and give me only the deliverable ones"
- "Check these signups for typos and fake addresses"
- "How many credits do I have left?"

Your agent gets five tools: `verify_email`, `verify_emails` (up to 1,000 at once), `clean_email_list`, `suggest_email_fix` (free) and `get_credit_balance`. It picks the right one by itself.

## Simple, fair pricing

- **Pay as you go.** No subscriptions, no monthly minimums.
- **Credits never expire.** Buy once, use them whenever.
- **Unknown results are free.** If a mail server doesn't answer, the credit goes back to you automatically.
- **Free checks stay free.** Bad syntax, missing mail servers and disposable domains never cost a credit.
- **250 free credits** when you sign up. No credit card required.

Packs start at $29 for 10,000 credits, with bonus credits on larger packs. See the [pricing page](/pricing) for every option.

## Built with your data in mind

Lists are encrypted in transit and never sold. API keys are stored only as one-way hashes, payments are handled entirely by Stripe, and you can ask us to delete your verification history at any time. Our [privacy policy](/privacy) has the details.

## Get started

[Create a free account](/sign-up) to get 250 credits, verify your first list in the dashboard, then grab an API key and connect your agent from the API & MCP page. If you have questions or feature requests, we'd love to hear them.