marginal is answering right now. Last checked 1 min ago.
Email A/B tests for AI agents: subject lines, managed sends, open/click tracking, and results.
Nothing serious here today
Today is the operative word: we check marginal every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add mcp --transport http https://marginal.sh/mcphttps://marginal.sh/mcp[mcp_servers.mcp]
url = "https://marginal.sh/mcp"{
"mcpServers": {
"mcp": {
"url": "https://marginal.sh/mcp"
}
}
}{
"servers": {
"mcp": {
"type": "http",
"url": "https://marginal.sh/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://marginal.sh/mcp | streamable-http | needs auth | 365 ms | 1 min ago |
Alternatives to marginal
same job, measured the same wayHands-on agent test results for small AI tools and MCP servers, live AI outages, malware name check.
Disposable test mailboxes on a real domain: send, receive and assert on real email.
Connect AI assistants to TestRail: manage test cases, suites, runs, results, and attachments.
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
Disposable email addresses for tests and agents: register, wait for mail, extract codes and links.
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Sendora's docs and API for coding agents: send test mail, read the log, set up webhooks.
MCP Server for software testing, test case management, test execution, and defect tracking.
marginal — questions
Answers built from our own checks of this server.