Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Testing With Sandbox

    3

    Safely capture and inspect test emails in a staging environment without sending to real recipients.

    Free

    4 usesSecurity scanned
    testing-with-sandbox

    testing-with-sandbox

    Example session with this skill installed

    Show me how to configure my Node.js app to send test emails to my Mailtrap sandbox inbox #123456.

    • Read your context and instructions
    • Compiled the testing-with-sandbox

    Install the mailtrap package, then use the following config:

    const { MailtrapClient } = require("mailtrap");

const client = new MailtrapClient({
  token: process.env.MAILTRAP_SANDBOX_TOKEN,
  testInboxId: 123456,
});

    Note: Ensure you use the Sandbox-specific API token.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Teaches agents to route outbound mail into a Mailtrap Email Sandbox (test inbox) so nothing reaches real recipients during development, staging, or CI. Covers both the HTTP Testing API (sandbox.api.mailtrap.io) and SMTP approach, how to obtain and use inbox_id, the separate sandbox token scope, and how to read and assert on captured messages via the Sandbox API. Includes SDK guidance and a common-mistakes table.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.

    • Cannot deliver mail to real recipients (testing only).
    • Requires separate API tokens for Sandbox vs Production.
    • Message retention varies by plan.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    4 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Listed5 months ago

    What's inside

    Frequently Asked Questions

    This skill allows your AI agents to simulate email sending by routing messages to a Mailtrap Sandbox, allowing you to inspect content and metadata without the risk of emailing real users during development or testing.

    The skill is designed to work with any LLM or AI agent framework that supports external API calls or SMTP configurations, and it includes logic for both the Mailtrap HTTP Testing API and standard SMTP relay.

    You will receive a modular prompt configuration, a technical guide on securing sandbox-specific API tokens, and a 'common-mistakes' checklist to ensure your agent doesn't accidentally use production credentials.

    Beyond just sending, this skill teaches your agent how to use the Sandbox API to programmatically retrieve, read, and perform assertions on captured emails to verify that automated workflows are functioning correctly.

    While you need an active Mailtrap account, this skill covers the specific setup for 'inbox_id' and the separate 'Sandbox' token scope, which are distinct from Mailtrap’s production bulk-sending API.

    New in Testing & Debugging

    Free