Check BounceBan credits, verify emails and read asynchronous bulk verification results. For marketers and operations teams using BounceBan to review contact addresses. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"bounceban": {
"url": "https://bounceban.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"bounceban": {
"type": "http",
"url": "https://bounceban.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
Read BounceBan verification credits and account rate limits before starting new checks. These allowances are shared across the account’s API keys.
bounceban_account
Confirm credit usage to verify one email. If the result is pending, keep its task ID and check that existing task later instead of submitting another verification.
Changes data · bounceban_verify_email bounceban_single_status
Confirm credit usage to submit 1–1,000 email addresses for asynchronous verification, then read the task’s progress and aggregate results. Wait between status checks.
Changes data · bounceban_create_bulk_verification bounceban_bulk_status
Check the task’s status, then read up to 100 existing email results. Follow further pages only when a continuation cursor is returned; pending tasks need time to finish.
bounceban_bulk_status bounceban_bulk_results
The login page asks for your BounceBan API key.
Find or create a key in BounceBan → API → Settings. Paste only the key, without a Bearer prefix. Connecting only reads your credit balance and rate limits. Verification tools require confirmation and can spend BounceBan credits. All keys in an account share credits, rate limits and any optional IP whitelist; per-key expiry and credit quotas also apply. If a key is rejected, check API Settings and verify your account email. Changing the key creates a separate UsefulAPI billing identity.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your BounceBan API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the BounceBan connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
bounceban_account | read | Read BounceBan credits and rate limits Read verification credit balance and account rate limits without starting verification. Limits and credit balance are shared across the account's API keys. |
bounceban_verify_email | write | Start BounceBan email verification Verify one email in regular mode. Costs verification credits on each request, including repeats, and requires confirm:true. Uses the standard API's 15-second result window; returns a final result or a queue/verifying task ID. Read that existing ID with bounceban_single_status later. Never resubmit simply because it is still pending. Basic-only mode can return unknown with score -1 for catch-all/SEG-protected addresses. |
bounceban_single_status | read | Read a BounceBan single verification Read an existing single verification ID without spending verification credits. Returns success, verifying or queue. Honor try_again_at when provided; poll no more than 10 times for an ID within 5 minutes, then stop. Results remain available for 90 days. This tool never starts another verification. |
bounceban_create_bulk_verification | write | Create a BounceBan bulk verification Submit 1–1,000 emails for regular-mode asynchronous verification. Starts a task and can consume verification credits; requires confirm:true. Check the dashboard before resubmitting after a lost/invalid response. greylisting_bypass:auto balances speed and accuracy; speed may yield more risky results; robust waits longer. No callbacks or automatic polling are configured. |
bounceban_bulk_status | read | Read BounceBan bulk task progress Read progress and aggregate results of an existing bulk task. Does not start verification. Wait between polls and honor account rate limits. importing/verifying status is still pending; finished means the task has ended. |
bounceban_bulk_results | read | Read one page of BounceBan bulk results Read up to 100 existing email results and a cursor for the next page. Results are retained for 90 days. No verification is started and no following page is fetched automatically. Omit state to get all processed results while a task is running; filtering by state can omit in-progress results. A pending response means wait and check the existing task later. |
bounceban_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
bounceban_request_feature | Request a missing feature Tell usefulapi that the user needs something the BounceBan tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
bounceban_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on BounceBan (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $39/month or $390/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
bounceban_cancel_subscription | Cancel the Pro subscription Cancel the caller's BounceBan Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run bounceban_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this BounceBan server only. Subscribe with bounceban_upgrade (it returns a Stripe Checkout link). Cancel any time with bounceban_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running bounceban_upgrade before then undoes the cancel. Or write to [email protected].
Check credits and account limits. Verify a single contact address. Verify a contact list in bulk. Review an existing bulk task’s results. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by BounceBan. The server calls the BounceBan API with your own BounceBan access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your BounceBan API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your BounceBan API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the BounceBan API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in BounceBan.
Yes, if you approve it. 2 of the 6 BounceBan tools can create or change data. The other 4 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this BounceBan server only. Cancel any time: Pro then runs to the end of the paid period. Run bounceban_usage_status to see how many calls you used.
Ask the AI to run bounceban_upgrade: it returns a Stripe Checkout link. To cancel, run bounceban_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with bounceban_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.