MCP server · Developer tools · official

Currents MCP server

Lets your AI read your Currents test results and help you fix failing Playwright tests.

Developer tools Coding For it and development Developer Tools

This is a helper made by Currents, the service that collects your automated test results from your build pipeline. Once you connect it, your AI assistant can look at your test runs and failures and help you figure out what went wrong. It is handy for anyone who runs automated browser tests and keeps seeing red results.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to Currents, the place where your test results live. So when you ask about a failing test, your AI can go look it up in Currents and answer with real data instead of guessing.

What this MCP server does

You ask your AI something about your tests, like why a run failed. Your AI uses this helper to talk to Currents. Currents sends back the runs, the failing tests, the error messages, and the steps that led to the failure. Your AI reads that and explains it to you or suggests a fix. You can also ask it to change things in Currents, like turning a quarantine rule on or off.

Flow diagram: you ask your AI “Why did my last Playwright run fail?”, the Currents MCP server connects it to Currents, and you get back plain chat answers.

Click to zoom

What you can do with it

List your recent test runs and see which ones failed
Find the error messages and steps for failing tests
See which tests are flaky over time
Look at performance numbers for your test files
Turn quarantine, skip, or tag rules on and off
Cancel or reset a run that is still going
Create or link a Jira issue from a failing test

Try asking your AI

“Why did my last Playwright run fail?”
“Show me the flakiest tests in this project over the past week.”
“Get the error details for the failing checkout test so I can fix it.”
“Cancel the run that is still in progress for the main branch.”

What it gives back to you

You get answers in plain chat: lists of runs, names of failing tests, error messages, and the steps that led up to each failure. It can also show trends, like which tests fail most often or how long your test files take. When it changes something in Currents, it tells you what it changed. Everything appears as text right in your conversation.

Before you start

What you need

A Currents account with at least one project
A Currents API key (a kind of password for apps; you get it from your Currents settings)
An AI tool that supports MCP servers, like Cursor or the Claude desktop app

Good to know

It can change or delete things in your Currents account, like cancelling runs or turning rules off, so be clear about what you want before you ask.

Install it with your AI

Add Currents MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Currents MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.