← All guides marginal.sh

Email Open Rate Tracking API for AI Agents

Updated June 2026 · Hosted email MCP server

If you're searching for an email open rate tracking API that an AI agent can call directly, marginal exposes open and click tracking through MCP tools — no glue code, no separate analytics dashboard to scrape.

What the open rate tracking covers

marginal is a hosted email MCP server that handles the send and the measurement together. When you launch a test, every variant is tracked for opens and clicks, and results come back as structured data your agent can reason over.

How tracking ties into a subject line A/B test

Open rate tracking is most useful when it's attached to a controlled experiment. With marginal you generate variants, launch the test, and let the platform record opens against each variant automatically.

Because the send and the tracking live in one place, you avoid stitching together a separate ESP and analytics layer just to learn which subject line won.

Calling it from an AI agent

The endpoint at https://marginal.sh/mcp speaks the Model Context Protocol, so any MCP-capable client can read open rate data as a first-class tool call. That makes AI agent email marketing workflows practical: the agent launches a test, waits, then queries open rates and decides what to send next.

Authentication is a Bearer API key (marg_live_...). Connect from Cursor, Claude Desktop, Claude Code, Windsurf, Cline, Continue, Zed, or OpenAI Codex — the open rate data surfaces the same way in each.

Getting started

The free tier includes 100 experiments per month, which is enough to wire up open rate tracking and run a few subject line A/B tests before committing. marginal is fully hosted, so there's nothing to deploy and no self-managed server to maintain.

Get started with marginal

marginal is a hosted email marketing MCP server at marginal.sh. Sign up free, create an API key, and connect https://marginal.sh/mcp from Cursor, Codex, or Claude Desktop.

Documentation · Sign up · FAQ