Now with a native MCP server for AI agents
Verify every email. Sniff out bounces before they hurt you.
BounceHound checks syntax, MX records and mailboxes to keep your lists clean and your sender reputation healthy. The difference: connect it to your favorite AI agent via MCP in one line and just ask it to clean your leads.
- Claude
- Cursor
- ChatGPT
- n8n
- + any MCP client
- No credit card required
- Credits never expire
- Unknowns are free
Try a single check
Demo · simulatedMailbox exists and accepts mail
- Role address
- No
- Disposable
- No
- Credit used
- 1
This preview uses sample logic. Sign up to run real checks against live mail servers.
claude mcp add --transport http bouncehound https://bouncehound.com/api/mcp \
--header "Authorization: Bearer YOUR_KEY"99%+accuracy on deliverable results
<300mstypical real-time API response
Freeunknown results never cost a credit
Forevercredits never expire
How it works
Four ways in. One clear answer out.
However your emails arrive, BounceHound sniffs each one and returns a simple status you can act on.
- Option 1
Upload a list
Drop in a CSV or XLSX with thousands (or millions) of rows.
- Option 2
Paste emails
Paste a handful of addresses straight into the dashboard.
- Option 3
Call the API
Verify at signup or in your pipeline with one REST request.
- Option 4
Ask your AI agent
Claude, Cursor or n8n call BounceHound over MCP for you.
Every email gets a status
Valid — Mailbox exists. Safe to send.
Invalid — Bad syntax, no mail server, or mailbox rejected. Remove it.
Risky / catch-all — Domain accepts everything. Send with care.
Disposable — Throwaway inbox. Usually not a real lead.
Unknown — Server didn't answer. Never charged.
AI agents · MCP
Ask your agent: “clean this lead list.”
BounceHound ships a native Model Context Protocol server. Plug it into the AI tools you already use and verification becomes a sentence, not a workflow.
You: Clean this lead list before I import it — leads.csv
Agent: Verified 1,284 emails with BounceHound: 1,102 valid, 97 invalid, 61 catch-all, 14 disposable, 10 unknown (free). Saved leads.clean.csv with only valid addresses and flagged 3 typos like jon@gmial.com → gmail.com.
- Tools for single checks, batch checks and credit balance — the agent picks the right one.
- Works anywhere MCP does: Claude Code, Claude Desktop, Cursor, ChatGPT connectors, n8n and more.
- Same API key, same credits, same results as the dashboard and REST API.
One command in your terminal. That's the whole setup.
claude mcp add --transport http bouncehound https://bouncehound.com/api/mcp \
--header "Authorization: Bearer YOUR_KEY"Add BounceHound as a remote MCP server in Cursor's MCP settings.
// ~/.cursor/mcp.json
{
"mcpServers": {
"bouncehound": {
"url": "https://bouncehound.com/api/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}Paste into your Claude Desktop config and restart the app.
// claude_desktop_config.json
{
"mcpServers": {
"bouncehound": {
"command": "npx",
"args": [
"mcp-remote", "https://bouncehound.com/api/mcp",
"--header", "Authorization: Bearer YOUR_KEY"
]
}
}
}Prefer plain HTTP? Every MCP tool is also a REST endpoint.
curl -X POST https://bouncehound.com/api/v1/verify \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"email":"jane@acme.com"}'{
"email": "jane@acme.com",
"status": "valid",
"reason": "mailbox_ok",
"role": false,
"disposable": false,
"didYouMean": null,
"charged": true
}Features
A nose for bad addresses
Everything you need to keep bounce rates low and inbox placement high — without the enterprise price tag.
Syntax + MX checks
Catches malformed addresses and domains that can't receive mail before a single SMTP probe.
Catch-all detection
Flags accept-all domains as risky so you can decide how aggressively to send.
Disposable detection
Spots throwaway inbox providers that fill your list with leads that vanish in ten minutes.
Role address detection
Identifies info@, sales@, support@ and other shared inboxes that rarely convert.
Typo suggestions
Suggests fixes like gmial.com → gmail.com so you recover real contacts instead of losing them.
Bulk CSV / XLSX
Upload big lists, keep your original columns, and download cleaned results by status.
Integrations
REST API, webhooks and MCP fit into Zapier-style automations, n8n flows and your own code.
GDPR-friendly
Encrypted in transit, minimal retention, and you can delete your lists at any time.
No subscriptions
Buy credits when you need them. No monthly fees, no seat pricing, no surprise renewals.
Pricing
Pay as you go. Credits never expire.
One credit verifies one email. Unknown results are refunded automatically. Start with 250 free credits — no card required.
10K credits
$29one-time
$2.90 per 1,000 emails
- 10,000 verifications
- API, MCP & bulk upload
50K credits
+5% Credit$99one-time
$1.89 per 1,000 emails
- 50,000 verifications
- +2,500 bonus credits
- API, MCP & bulk upload
- Most popular
100K credits
+5% Credit$169one-time
$1.61 per 1,000 emails
- 100,000 verifications
- +5,000 bonus credits
- API, MCP & bulk upload
500K credits
+10% Credit$599one-time
$1.09 per 1,000 emails
- 500,000 verifications
- +50,000 bonus credits
- API, MCP & bulk upload
1M credits
+10% Credit$999one-time
$0.91 per 1,000 emails
- 1,000,000 verifications
- +100,000 bonus credits
- API, MCP & bulk upload
- Pay as you go — no subscription
- Credits never expire
- Unknown results are free
Compare
Built for how teams work now
How BounceHound stacks up against the typical email verification service.
| Feature | BounceHound | Typical competitors |
|---|---|---|
| Native MCP server for AI agents | Yes | No |
| Pay-as-you-go credits (no subscription) | Yes | Varies |
| Credits never expire | Yes | Often 6–12 months |
| Unknown results refunded | Yes | Varies |
| Catch-all, disposable & role detection | Yes | Yes |
| Typo suggestions (did you mean…) | Yes | Varies |
| REST API & bulk CSV/XLSX | Yes | Yes |
| Free credits on signup | 250 | Often 100 or fewer |
“Typical competitors” reflects common industry practice; individual services vary.
FAQ
Questions, fetched
What is a credit?
One credit verifies one email address. Duplicates in a bulk upload are removed before you're charged, and results that come back unknown are refunded automatically.
Do credits expire?
No. Credits you buy stay in your account until you use them — there's no subscription and nothing renews.
What is MCP and why does it matter?
The Model Context Protocol is an open standard that lets AI assistants call external tools. With BounceHound's MCP server connected, you can ask Claude, Cursor or another MCP client to verify an address or clean a list and it will call BounceHound directly.
What does “risky” or “catch-all” mean?
Some domains accept mail for any address, so the mailbox can't be confirmed. We flag these as risky so you can choose whether to send. Many teams send to them in smaller, separate batches.
Which file formats can I upload?
CSV and XLSX. We detect the email column automatically and keep your other columns intact in the download.
How do you handle my data?
Lists are encrypted in transit and stored only as long as needed to deliver results. You can delete uploaded lists from your dashboard at any time. We never sell or share your data.
How do I get started?
Create an account to get 250 free credits — no card required. Then upload a list, call the API, or connect your AI agent with one line.
Put the hound on your list.
Get 250 free credits, verify your first list in minutes, and connect your AI agent whenever you're ready.