Bouncer
for LuumenAI
Verify email addresses and run batch checks without leaving the terminal
Connect Bouncer and Luumen can check a single address, verify a sending domain, and pull batch results while you work. Credit balance is one question away. When a list needs verifying, the agent sets up the batch request as a previewed step you approve first. Authentication is by API key.
The Bouncer toolbox
10 tools: 5 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCheck Toxicity List Job StatusCheck the status of a specific toxicity list job.
- ReadGet Batch ResultsRetrieve the results of a batch verification process.
- ReadGet CreditsRetrieve the current credit balance for the account.
- ReadVerify DomainVerify the validity and configuration of a domain.
- ReadVerify EmailVerify a single email address in real-time.
- WriteCreate Batch RequestInitiates an asynchronous batch email verification request. Approval by default
- WriteCreate Toxicity List JobCreate a toxicity analysis job for a list of email addresses. Approval by default
- WriteDelete batch requestDeletes a batch email verification request and all associated emails and results. Approval by default
- WriteDelete Toxicity List JobDelete a specific toxicity list job. Approval by default
- WriteFinish BatchMark a batch verification process as finished early. Approval by default
One prompt, start to finish
What a governed Bouncer run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create batch request, create toxicity list job, delete batch request, delete toxicity list job, and more — is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Bouncer — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
SlackRead the incident thread; post updates and approvals back.
GmailVendor and alert mail as context; replies drafted for review.
Microsoft TeamsRead Teams channels and chats for context, then make membership changes as approved steps.
DiscordRead Discord command permissions and app context, then change them with approvalPut Bouncer to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.