marginal MCP Server

by marginal Your server? Claim it

answering

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.

Uptime history 47 days of history · worst day 97%

47 days agonow

100.0%

Uptime 24h

92 of 92 checks

—

Tools

hidden behind auth

446 ms

Response time

average over 24h

authentication required

Access

streamable-http

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp --transport http https://marginal.sh/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://marginal.sh/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://marginal.sh/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://marginal.sh/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "mcp": {
      "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	837 ms	1 min ago

Alternatives to marginal

same job, measured the same way

fixture.email — Email Testing for Agents

by fixture

Disposable test mailboxes on a real domain: send, receive and assert on real email.

answering

Playwright Report MCP

by hubertgajewski

Run Playwright tests and surface structured results for AI agents doing test failure analysis.

171 installs/wk local only

Evalview MCP

by hidai25

Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.

984 installs/wk local only

Qatouch

by qatouch

MCP Server for software testing, test case management, test execution, and defect tracking.

113 installs/wk local only

Sheetspec

by helloo1568

Contract testing and quality gates for spreadsheets created by AI agents.

50 installs/wk local only

Splera

by sohaibt

A/B testing for vibe coders: create, track, and ship experiments from your AI coding agent.

20 installs/wk local only

MCP Test Runner

by lovranran

Local test execution and coverage summaries for onboarding agents.

63 installs/wk local only

App Manager

by lance

App Store Connect operator for AI agents: icons, TestFlight builds, listings, IAP, rejection fixes.

answering

marginal — questions

Answers built from our own checks of this server.

Why is there no tool list for marginal?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is marginal working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 446 ms. The bar chart above shows every period we have measured.

How do I connect marginal?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own credentials: it refuses anonymous clients.

Does marginal need an API key?

Yes. Every time we knock, marginal answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is marginal?

It answers our handshake in 446 ms on average, which is faster than 33% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.