Connect a coding agent
to email over MCP.

Connect a coding agent to NoticeAPI over hosted MCP or local stdio. It discovers the email tools, acts only where its API key allows, and proves the path in the simulator before real mail.

  • OAuth or bearer key
  • Project-scoped access
  • Deterministic testing
Hosted MCP
mcp client config
{
  "mcpServers": {
    "noticeapi": {
      "type": "http",
      "url": "https://mcp.noticeapi.com/mcp",
      "headers": { "Authorization": "Bearer ntc_…" }
    }
  }
}
Streamable HTTPOAuth or scoped key

Agent-ready by design

Give a coding agent one clear email job.

MCP helps a coding client discover the project, prepare the email path, test an outcome, and inspect the recipient event trail. It is a tool connection for the coding agent, not a hosted always-running agent.

Read the agent guide
ClaudeCursorWindsurfGitHub Copilot
Setup prompt

Copy a ready-to-run instruction for your agent. It connects with least privilege, proves the simulator path, and waits for you before real delivery.

  • Choose the projectKeep the agent inside the project and sender domains you approve.
  • Test in the simulatorUse deterministic recipients before a real mailbox is involved.
  • Inspect the resultRead the recipient timeline before you move the workflow to production.

For agents you run

Use the email APIs in your always-running agent.

Your worker can send transactional email and handle signedemail.received events. On a paid workspace, it can also fetch inbound messages with a receiving API key. NoticeAPI moves the email. You operate the model, queue, and decisions.

Coding agent

Use MCP in an MCP-capable client to implement and test the integration.

Read MCP setup
Always-running agent

Run your own worker, then receive inbound events and make direct outbound API calls.

Read inbound email setup

Bounded authority

An agent can only use what its API key allows.

Bind access to a project, chosen domains, and the capabilities the job needs. Sending, scheduling, and outcome reads can stay available while broader workspace operations remain out of reach.

  • Project and domain boundaries are enforced on every tool call
  • Quotas, suppressions, and deliverability pauses still apply
  • Side effects and destructive tools are machine-readable
Explore scoped keys
API keyproject_123
Fullall capabilities

Every allowed capability inside one project.

Sendingemail:send

Send, schedule, and read recipient outcomes.

Customselected scopes

Choose capabilities, projects, and domains by hand.

Authority can narrow, never widen.A key created from this one is equal to or narrower than its parent.

One tool catalog

From first project to recipient outcome.

Give the agent only the job it needs today. Add capabilities later without changing the connection or teaching it another provider.

See every MCP tool
CapabilityScopesWhat the agent can do
Projects and accessprojects:* · api-keys:write

List and operate projects, then issue or revoke keys no broader than the caller.

Transactional emailemail:send

Send, batch, schedule, cancel, reschedule, and inspect recipient outcomes.

Domainsdomains:read · domains:write

Create, inspect, verify, and remove sender domains.

Templatestemplates:write

Create, inspect, update, and remove stored templates.

Marketingaudiences · broadcasts · automations

Operate opted-in contacts, broadcasts, and automations.

Receivingreceiving:read · receiving:write

Manage API receiving domains and read inbound messages.

Operationswebhooks · suppressions

Manage signed event endpoints and recipient suppression state.

Test first

Prove the whole flow without mailing a real person.

The simulator exercises the send, status, webhook, and suppression pipeline with deterministic recipients. Your agent can see the result and fix the integration before it touches a verified sender.

  1. Send from the sandboxdemo@sandbox.noticeapi.comNo sender reputation is involved.
  2. Choose the outcomedelivered@simulator.noticeapi.comDelivered, bounced, complained, or suppressed.
  3. Exercise the real event pathThe simulator fires the same signed x-noticeapi-* events.
  4. Read the recipient timelineThe agent fetches the result and can correct the workflow.

Ready for an agent?

Give the agent tools inside a fixed boundary.

Create a project-scoped key, connect MCP, and let the agent prove the email path in the simulator first.