Imagine you could just ask whether last night's test run passed, find out which tests are flaky, or pull up the trace for a failing test — all without opening NeetoPlaydash, clicking through projects, or scrolling through run after run.
NeetoPlaydash works with AI assistants you may already be using, like Claude, Cursor, and GitHub Copilot. Once you connect them together, your AI assistant can fetch your test runs, inspect failures, and check how a test has behaved over time. You simply ask in plain English and the assistant does the work.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard that lets AI assistants and apps like NeetoPlaydash speak the same language. You do not need to understand how it works to use any of the steps below — think of it as the plumbing that connects your AI assistant to your NeetoPlaydash workspace.
Why this is useful
Think of it as giving your AI a passcode to your NeetoPlaydash test results. After that, the usual back-and-forth disappears. A few examples of what becomes possible:
- You ask, "Did last night's run on the main branch pass?" and the assistant checks for you.
- You ask, "Which tests failed in the latest run?" and you get the list on the spot.
- You say, "Show me only the flaky tests from this run," and it filters them out for you.
- You ask, "Has this test been failing recently, or is this new?" and the assistant pulls up its history.
You do not need to be technical to benefit from this. If you already talk to an AI assistant for other things, you can talk to it about your NeetoPlaydash test runs too.
What you need to get started
Two things:
1. An AI assistant that supports this kind of connection (we cover the popular ones below).
2. A NeetoPlaydash API key, which authenticates the assistant with your workspace. See the Getting Started help article for how to generate one.
That is it. Once you have both, you paste a small snippet of settings into your AI tool and you are done.
Connecting your AI assistant to NeetoPlaydash
Pick the tool you use. You only need to follow the steps for that one; you can skip the rest. Each section shows a small block of settings — copy it, replace YOUR_API_KEY with your own key, and save.
Claude Code
Open the file ~/.claude.json and paste the following (if the file already has settings, add just the neetoplaydash entry inside mcpServers):
{
"mcpServers": {
"neetoplaydash": {
"type": "http",
"url": "https://connect.neetoplaydash.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save the file and restart Claude Code.
Cursor
Open ~/.cursor/mcp.json and paste the following:
{
"mcpServers": {
"neetoplaydash": {
"url": "https://connect.neetoplaydash.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save it and restart Cursor (or reload the window via the command palette).
VS Code with GitHub Copilot
Create or open .vscode/mcp.json in your workspace and paste:
{
"servers": {
"neetoplaydash": {
"type": "http",
"url": "https://connect.neetoplaydash.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}VS Code will ask you for your API key the first time. You need VS Code 1.99 or newer, and you must be in the Copilot chat's Agent mode to use it.
Windsurf
Open ~/.codeium/windsurf/mcp_config.json and paste:
{
"mcpServers": {
"neetoplaydash": {
"serverUrl": "https://connect.neetoplaydash.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save it and make sure the connection is turned on in Settings > Cascade > MCP Servers. Windsurf has a limit of 100 total tools across all connected services, so if it complains, turn a few other connections off.
Try it out
Once you are connected, the easiest way to see what is possible is to just ask. Here are some prompts you can copy and paste to get a feel for it:
- "List all my projects."
- "Show the latest runs for this project on the main branch."
- "Which tests failed in the most recent run?"
- "Show me only the flaky tests from this run."
- "Get the full details of this run."
- "Has this test failed in recent runs, or is this a new failure?"
- "Get the Playwright trace for the failing checkout test."
- "Summarize what went wrong in last night's run."
What your AI assistant can actually do
Under the hood, the connection gives your AI assistant a set of abilities. You do not need to remember any of these names — just ask naturally and the assistant picks the right one. But here is the full list if you are curious.
Finding projects and runs: list all projects in your workspace, list the runs for a project (filtered by branch or by status such as passed, failed, or running), and get the full details of a specific run.
Inspecting tests: list the specs and tests in a run (filtered by status such as failed or flaky), and get the details of a single test, including how it behaved across shards and retries.
Debugging failures: fetch the Playwright trace viewer links for a run or for a specific test, so you can dig into the screenshots, DOM, network calls, and console logs captured at the point of failure.
Test history: check how a test has performed across recent runs to tell whether a failure is brand new or a long-standing flake.
The connection is read-only — your AI assistant can look at your projects, runs, tests, and traces, but it cannot change or delete anything in your workspace.