Integration

Bouncer integration

Bouncer is an email verification service. An agent can verify one email address in real time (deliverability status, reason, score, role, disposable and free-provider flags), verify lists in asynchronous batches (create, check status, download results, finish early, delete), verify a list synchronously through the batch queue, check a domain's MX records and catch-all behaviour, score lists for toxicity (spam traps, complainers, breached addresses) and read the remaining credit balance. Every verification consumes credits. Authentication is an API key sent in the x-api-key header.

Connect Bouncer How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Bouncer.Built from the 13 Bouncer tools below, on the connection you add once.

What you can do with Bouncer

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Batch, 4 operations

create_batchCreate batchPOSTStart an asynchronous verification of up to 100,000 addresses (one credit each). Returns batchId: poll get_batch until status is completed, then call get_batch_results.
delete_batchDelete batchDELETEDelete a batch and the emails associated with it. Its results are lost and cannot be downloaded afterwards.
finish_batchFinish batchPOSTStop a running batch early: Bouncer finishes processing and returns the credits of addresses not yet verified. Download results once get_batch reports status completed.
get_batchGet batchGETRead the state of a batch created by create_batch: status (queued, processing, completed), counts and credits used. Poll every 10 to 30 seconds until status is completed, then call get_batch_results.

Toxicity job, 3 operations

create_toxicity_list_jobCreate toxicity list jobPOSTStart a toxicity scoring job on a list of addresses (spam traps, complainers and similar risks). Returns id: poll get_toxicity_list_job until status is completed, then call get_toxicity_list_results. 10 jobs per minute.
delete_toxicity_list_jobDelete toxicity list jobDELETEDelete a toxicity list job and its results, which can no longer be downloaded afterwards.
get_toxicity_list_jobGet toxicity list jobGETRead the state of a toxicity list job created by create_toxicity_list_job. When status is completed, call get_toxicity_list_results.

Batch result, 1 operation

get_batch_resultsGet batch resultsGETDownload the verification results of a completed batch (see get_batch), one record per address, optionally only the addresses with a given status.

Credit, 1 operation

get_creditsGet creditsGETReturn the number of verification credits left on the account. Limited to 10 calls per minute.

Domain, 1 operation

verify_domainVerify domainGETCheck one domain (charges one credit): whether it is catch-all, disposable or a free provider, its MX or A record, and its SMTP provider.

Email, 1 operation

verify_single_emailVerify single emailGETVerify one email address in real time (charges one credit): returns status, reason, score and domain and mailbox flags. Waits up to timeout seconds (default 10, max 30). For many addresses use create_batch.

Email batch, 1 operation

verify_batch_syncVerify batch syncPOSTVerify up to 10,000 addresses through the batch queue and wait for the results (one credit each, results kept 24 hours). Limited to 100 calls per minute; space calls 5 seconds to 10 minutes apart.

Toxicity result, 1 operation

get_toxicity_list_resultsGet toxicity list resultsGETDownload the results of a completed toxicity list job: each address with its toxicity level from 0 to 5 (4 and 5 are best suppressed).

Use Bouncer from Claude Code, Cursor or Codex

Connect Bouncer in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Bouncer operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Bouncer

Create your workspace
Sign up free. Nothing to install.
Connect Bouncer once
Add your Bouncer connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.