Bouncer MCP integration for AI agents.
Connect AI agents to Bouncer through 13 structured actions, including create toxicity list job, create batch request, delete batch request, and finish batch.…
- ACTION CONTRACTS
- 13
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Bouncer integration exposes
The Bouncer Agent App exposes 13 provider-backed actions for communication and marketing work. Its current contract lets an authorized agent create a bouncer toxicity list job for multiple email addresses, create an async bouncer batch verification request for multiple email addresses, and delete a bouncer batch verification request and its stored results. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Bouncer account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Bouncer capabilities.
Showing 12 of 13 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
create_toxicity_list_jobREADCreate a Bouncer toxicity list job for multiple email addresses.
INPUTS: emails
create_batch_requestWRITECreate an async Bouncer batch verification request for multiple email addresses.
INPUTS: emails / callbackUrl
delete_batch_requestHIGH IMPACTDelete a Bouncer batch verification request and its stored results.
INPUTS: batchId
finish_batchREVIEWRequest early completion for a Bouncer batch verification request.
INPUTS: batchId
delete_toxicity_list_jobHIGH IMPACTDelete a Bouncer toxicity list job and its stored results.
INPUTS: id
get_batch_resultsREADDownload normalized results from a completed Bouncer batch verification request.
INPUTS: batchId / download
get_batch_statusREADGet the current processing status of a Bouncer batch verification request.
INPUTS: batchId / includeStats
get_creditsREADGet the current Bouncer credit balance.
get_toxicity_list_job_statusREADGet the current processing status of a Bouncer toxicity list job.
INPUTS: id
get_toxicity_list_resultsREADDownload normalized results from a completed Bouncer toxicity list job.
INPUTS: id
verify_domainREVIEWVerify one domain with Bouncer and inspect its DNS and catch-all signals.
INPUTS: domain
verify_emailREVIEWVerify a single email address with Bouncer in real time.
INPUTS: email
INPUT CONTRACTS
Know what the action needs before it runs.
create_toxicity_list_job
emailsREQUIRED- The email addresses to verify with Bouncer.
create_batch_request
emailsREQUIRED- The email addresses to verify with Bouncer.
callbackUrlOPTIONAL- The callback URL Bouncer should notify after batch processing completes.
delete_batch_request
batchIdREQUIRED- The batch identifier returned by Bouncer.
finish_batch
batchIdREQUIRED- The batch identifier returned by Bouncer.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Create Toxicity List Job
Create a Bouncer toxicity list job for multiple email addresses. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
create_toxicity_list_jobControl Create Batch Request
Create an async Bouncer batch verification request for multiple email addresses. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_batch_requestVerify with Get Batch Results
Download normalized results from a completed Bouncer batch verification request. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_batch_resultsSAFETY BOUNDARY
Operate Bouncer with explicit limits
- Authorize Bouncer with API key and grant only the provider access required by the selected actions.
- 3 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_batch_request` and `delete_toxicity_list_job` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Bouncer rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Bouncer task completed successfully.
CONNECTION MODEL
API key
Bouncer API key sent with the x-api-key header.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 6
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 2
- REVIEW SIGNALS
- 4
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Bouncer.