mailflat-mcp
MCP server that gives an agent its own email inbox: it opens the inbox, waits for the one-time code a signup sends, and reads or sends mail. Addresses are permanent, so a test suite does not need a new one per run; only the messages expire, on a retention window you set.
README
MailFlat SDKs
Official client libraries for MailFlat: email inboxes your code owns, with one-line OTP retrieval. Built for test suites (Selenium, pytest, Playwright) and AI agents.
Addresses are permanent, so a suite does not need a fresh one per run. Only the messages expire, on a retention window you choose.
This repo holds only the open-source SDKs. The MailFlat service itself is closed-source.
Packages
| Package | For | Install |
|---|---|---|
mailflat |
Python | pip install mailflat |
@mailflat/sdk |
JavaScript / TypeScript | npm i @mailflat/sdk |
mailflat-mcp |
AI assistants (Claude, Cursor) — MCP | uvx mailflat-mcp |
@mailflat/ai-sdk |
Vercel AI SDK agents | npm i @mailflat/ai-sdk |
mailflat.langchain |
LangChain agents | pip install "mailflat[langchain]" |
mailflat-sdk (Java) |
Java / Selenium | via JitPack — see below |
Each client is a thin, typed wrapper over the same /api/v1 Agent API, so they behave identically.
Authenticate with your account key (mf_live_…) from the dashboard (Agents → API keys).
Java / Selenium (JitPack)
JitPack derives the
groupIdfrom the GitHub owner. This repo moved to the officialMailFlataccount in August 2026, so releases fromv0.4.4on publish ascom.github.MailFlat:mailflat-sdks. Earlier versions still resolve under the old coordinatecom.github.onderyentar21:mailflat-sdks; the old repo stays up for them. The client is moving to Maven Central (net.mailflat) next, which ends the owner coupling.
<repositories>
<repository><id>jitpack.io</id><url>https://jitpack.io</url></repository>
</repositories>
<dependency>
<groupId>com.github.MailFlat</groupId>
<artifactId>mailflat-sdks</artifactId>
<version>v0.4.5</version>
</dependency>
MailFlat mf = new MailFlat("mf_live_…");
Inbox inbox = mf.create("signup");
driver.findElement(By.id("email")).sendKeys(inbox.address());
String otp = inbox.waitForOtp(30); // polls until the code arrives
driver.findElement(By.id("code")).sendKeys(otp);
Quick examples
Python
from mailflat import MailFlat
mf = MailFlat(api_key="mf_live_…")
inbox = mf.create(label="signup")
otp = inbox.wait_for_otp(timeout=30)
JavaScript / TypeScript
import { MailFlat } from "@mailflat/sdk";
const mf = new MailFlat({ apiKey: process.env.MAILFLAT_API_KEY });
const inbox = await mf.create({ label: "signup" });
const otp = await inbox.waitForOtp({ timeout: 30000 });
License
MIT. The full text is in LICENSE at the repository root; each package directory carries an identical copy.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.