BounceBan MCP server
Check email deliverability and follow the verification result before scheduling another check. Arc0’s BounceBan tools are in early access; verification can spend provider credits even when a request times out. Access is gated: request enablement for your organization before connecting.
Working with BounceBan
Before verifying an address, use bounceban.get_account to inspect the account’s verification balance and endpoint limits. Verification credits and Check Plan credits are separate balances. An available balance does not establish permission to process a person’s address; choose addresses you are authorized to check.
For one address, bounceban.verify_single submits a paid verification and may return a queued result. Retain its identifier so your agent can check progress with bounceban.get_single_status. Respect the suggested retry time and the limit of ten status calls per five minutes. A timeout can leave the paid submission’s outcome unknown, so do not submit another check merely because the first response was lost.
Use bounceban.check when you need syntax or disposable-domain classification rather than SMTP verification. It uses separate Check Plan credits. For an existing bulk task, read bounceban.get_bulk_status before requesting up to one hundred exact addresses through bounceban.get_bulk_emails. An unfinished task can return an error; empty results do not establish deliverability. These tools inspect existing bulk work and do not create a new bulk verification task.
Agent workflows for BounceBan.
Check the credit balance
Read bounceban.get_account for account limits before starting verification work.
Verify one address
Submit bounceban.verify_single for an authorized address and retain the returned verification identifier.
Follow a queued check
Read bounceban.get_single_status until the verification completes, respecting the polling limit and suggested retry time.
Inspect selected bulk results
Check bounceban.get_bulk_status before retrieving exact addresses with bounceban.get_bulk_emails.
6 BounceBan actions, graded by risk.
These actions come from the Arc0 registry. Your identity, provider permissions and Arc0 policies determine which actions can run.
read
5Look things up, subject to your permissions.
- bounceban.get_accountGet account limits
Get verification credit balance and per-endpoint rate limits. Use when planning checks or diagnosing exhausted credits; Check Plan credits are a separate balance.
- bounceban.get_single_statusGet email verification status
Read a single verification by id without spending verification credits. Use when a submitted email is queued or verifying; respect try_again_at and limit polling to 10 calls per five minutes. Results expire after 90 days.
- bounceban.checkCheck email or domain type
Classify an email or domain and check email syntax without SMTP verification. Use when screening disposable or free addresses; costs 1 separate Check Plan credit per successful request.
- bounceban.get_bulk_statusGet bulk task progress
Read progress and summary counts for an existing bulk verification task. Use when checking whether an owned task has finished before retrieving specific email results.
- bounceban.get_bulk_emailsGet selected bulk results
Read verification results for up to 100 exact emails in an owned bulk task. Use when retrieving selected results without exporting the entire list. An err result indicates the task is not finished; empty items mean no matching results.
write
1Create and change things. Allow, or ask the user first.
- bounceban.verify_singleVerify one email
Submit one email for SMTP verification. Use when checking deliverability; costs 1 credit per request. Poll the returned id when queued or verifying. A timed-out call may still be charged; do not blindly resubmit.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Control access to BounceBan.
After early access is enabled, connect the intended BounceBan account, authorize your AI client and set policies for its tools.
Provider permissions and Arc0 policy both apply. Allow reads, require approval for selected writes, or deny destructive actions. The audit log records execution decisions.
Configure policies and approvalsExample policy choices
- Read actions: allow where authorized
- bounceban.verify_single: require approval
Arc0 MCP endpoint: https://api.arc0.ai/mcp
How BounceBan connects.
Connect BounceBan using API key. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.
The connection serves authorized calls through Arc0 MCP and REST. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use BounceBan with your AI client.
Request access to BounceBan first. An Arc0 administrator must enable it for your organization before these actions appear. Then authorize your AI client separately. It only receives tools and accounts allowed for that identity.
BounceBan with Claude
Claude Desktop + Claude Code
- In Claude Desktop, add Arc0 through the remote MCP settings and use OAuth. Follow the generic remote-client steps if your account’s interface differs.
- For Claude Code, run the command below. Open /mcp, select Arc0, and authenticate in your browser. Select your workspace and review access.
- Check the connection with claude mcp get arc0.
claude mcp add --transport http --scope user arc0 https://api.arc0.ai/mcpBounceBan with ChatGPT
ChatGPT on the web
- Open Plugins in ChatGPT, select the plus button, then Add custom MCP server.
- Name it Arc0, enter the server URL below, and choose OAuth. Use dynamic client registration if asked; no Arc0 API key is needed.
- Review the notice and select Create as a plugin. Complete Arc0 sign-in, workspace selection and consent, then install and select the plugin in your conversation. Labels and access vary by account; managed workspaces may require administrator approval.
https://api.arc0.ai/mcpBounceBan with OpenAI Codex
Codex app + CLI
- Run the registration command below. The app and CLI share ~/.codex/config.toml.
- Complete browser OAuth, choose your Arc0 workspace, and review access. If authentication does not start, run codex mcp login arc0.
- Check codex mcp list, then open a new Codex chat. Inspect an existing arc0 entry before changing it.
codex mcp add arc0 --url https://api.arc0.ai/mcpBounceBan with Cursor
Remote MCP setup
- Add Arc0 in your client’s remote MCP settings using the server URL below.
- Choose OAuth, sign in to Arc0, select the intended workspace and review access.
- Confirm the server is connected and start with an allowed read. These are generic remote-MCP steps; consult your client’s settings for its current interface.
https://api.arc0.ai/mcpBounceBan with VS Code
Remote MCP setup
- Add a remote HTTP MCP server named Arc0 using the URL below.
- Use OAuth and finish Arc0 sign-in, workspace selection and consent.
- Confirm discovery succeeds before requesting a read. These are generic remote-MCP steps; client UI and availability may differ.
https://api.arc0.ai/mcpBounceBan with Any MCP client
Streamable HTTP
- Use a client that supports remote MCP over Streamable HTTP. Add the server URL below and choose OAuth.
- For a client without OAuth, use a self-bound API key with execute permission in the X-API-Key header. Store it in secret storage or an environment variable, outside source control. Never send both an API key and an OAuth bearer token.
- Use the MCP clients guide for the SDK transport example and Embedded identity for business-managed end users.
https://api.arc0.ai/mcpAfter setup, ask your agent to find an allowed read action, load its schema, and execute it on the intended account. Check Activity for the receipt. A connected MCP client alone does not confirm a successful provider call.
BounceBan and Arc0, answered.
Does a queued check mean the address is deliverable?
No. Keep the verification identifier and read its status until a result is available. A timeout is not a reason to submit another paid check.
Does verification spend provider credits?
Single verification costs one credit per request. Classification uses separate Check Plan credits. Check provider balances before starting.
Can my agent start a bulk task?
No. The current actions inspect existing bulk tasks and selected results; they do not create a bulk task.
Can I use these tools with Claude and Codex?
After early access is enabled for your organization, connect the intended account and authorize a compatible MCP client. Its tools follow the identity’s permissions.
Does an API key refresh automatically?
API keys do not refresh. Replace or revoke them at BounceBan; disconnecting removes access through Arc0.
Request BounceBan access.
BounceBan MCP server: 6 actions including get account limits, verify one email, get email verification status. Request early access through Arc0.
Free to build · MCP + REST · Audit log on every plan
BounceBan and its logo are trademarks of their respective owners. Arc0 is not affiliated with or endorsed by BounceBan.