Email for AI agents.

Email for AI agents. Your AI agents can send email, manage domains, and check delivery status - no SDK needed. One URL, one API key, 20 tools.

Claude Cursor Windsurf Continue Cline Zed + any MCP client

How it works

Three steps. No code. No SDK. Just a config file edit.

1

Get an API key

Sign up free and copy your re_live_... key. Free tier works.

POST /auth/register {"name":"Acme","email":"you@acme.com", "password":"..."}
2

Paste the MCP config

Edit your AI client's MCP config. One URL, one Authorization header.

{ "mcpServers": { "sparked-mail": { "url": "https://mail.sparked.network/mcp", "headers": { "Authorization": "Bearer re_live_xxx" } } } }
3

Ask your agent

Your agent now knows how to send email and manage domains.

"Send Alice a welcome email from noreply@acme.com"
MCP integration flow: AI agent calls send_email tool via MCP server, which calls Sparked Mail API

What your agent can do

Six example prompts. Each one is a few tool calls the AI figures out on its own.

1

"Send Alice a welcome email"

Agent calls list_templates, picks "Welcome", then calls send_with_template with Alice's name. Done in two tool calls.

list_templates → send_with_template
2

"Set up my domain"

Agent calls add_domain, returns TXT records, waits for you to publish DNS, then calls verify_domain.

add_domain → verify_domain
3

"Did that email bounce?"

Agent calls get_message_status, reports delivery state, suggests next steps if it failed.

get_message_status
4

"Notify our server when emails bounce"

Agent calls setup_webhook with the URL you give it. Returns the HMAC secret to save on your side.

setup_webhook
5

"Block this recipient"

Agent calls add_suppression with the email. Future sends to that address are blocked at the API level.

add_suppression
6

"Enable inbound replies"

Agent calls enable_inbound, returns a one-click Cloudflare Worker deploy URL for you to click.

enable_inbound

Try it

Pick your AI client, copy the config. That's the whole integration.

// ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "sparked-mail": {
      "url": "https://mail.sparked.network/mcp",
      "headers": {
        "Authorization": "Bearer re_live_xxx"
      }
    }
  }
}
// Settings -> MCP -> Add new MCP server
Type: http
URL: https://mail.sparked.network/mcp
Headers: Authorization: Bearer re_live_xxx
// ~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "sparked-mail": {
      "serverUrl": "https://mail.sparked.network/mcp",
      "headers": {
        "Authorization": "Bearer re_live_xxx"
      }
    }
  }
}

Prefer the CLI? Claude Code users can run:

claude mcp add --transport http sparked-mail https://mail.sparked.network/mcp \
  --header "Authorization: Bearer re_live_xxx"

20 tools available

Every common email operation is a single tool call. Your agent figures out which to call.

send_email

Send a transactional email

send_with_template

Send using a stored Handlebars template

get_message_status

Check delivery / open / click state

list_domains

List verified sending domains

add_domain

Add a new sending domain

verify_domain

Verify domain via live DNS lookup

list_inboxes

List allowed sender local-parts

add_inbox

Register a new sender identity

list_templates

List stored templates

create_template

Create a Handlebars template

list_suppressions

List blocked recipients

add_suppression

Block a recipient (unsubscribe)

remove_suppression

Unblock a recipient

get_usage

Current rate-limit usage

list_recent_events

Recent delivery events

setup_webhook

Configure webhook URL + secret

create_subaccount

Create a subaccount (agency)

list_api_keys

List API keys on the account

enable_inbound

Enable inbound (CF Email Routing)

check_spf

Check SPF record status

Safety rails

Your AI agent can't lock you out or destroy data. Destructive operations are REST-only.

Read-only auto-approve

Tools like list_domains, get_usage, list_recent_events can be auto-approved by clients - no confirmation needed.

  • list_domains, list_inboxes
  • get_message_status, get_usage
  • list_recent_events, list_templates
  • list_suppressions, list_api_keys
  • check_spf

Mutations require confirm

send_email, add_domain, setup_webhook, add_suppression - clients prompt for user confirmation by default.

  • send_email, send_with_template
  • add_domain, verify_domain
  • add_inbox, create_template
  • setup_webhook, add_suppression
  • remove_suppression, enable_inbound
  • create_subaccount

Destructive ops blocked

Delete domain, delete template, rotate API keys, delete account - all REST-only. Agents can't accidentally destroy their own access.

  • DELETE /domains/:id
  • DELETE /templates/:id
  • POST /api-keys/rotate
  • DELETE /admin/accounts/:id
  • Account deletion

Start free. No credit card required.

1,000 emails per month, DKIM signed, webhooks, MCP support. Upgrade when you need more.