# Playrunner

Playrunner connects an AI agent to Playwright workflows in the cloud, so it can launch checks and inspect their results. Use it to rerun browser tests after code changes.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 3
- Author: playrunner
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/playrunner/playrunner
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/playrunner

## What it does

The MCP server links an agent to Playrunner Cloud. It can find projects, create workflows, start runs, and inspect their results. Reports include logs and run artefacts such as traces, screenshots, and video.

Build a workflow from an existing Playwright repository or an inline script. Choose an environment, optionally select an Authentication Profile, then pick local Docker, managed cloud runners, or self-hosted execution. Saved workflows can also be used by teammates and CI.

The connection requires an MCP client that supports remote Streamable HTTP and OAuth. A shell-capable agent can use the CLI instead. Starting a job does not mean its tests passed, so check the report before treating the run as successful.

## Requirements
- Remote server: `https://playrunner.cloud/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://playrunner.cloud/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add playrunner --url https://playrunner.cloud/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "playrunner": {
            "url": "https://playrunner.cloud/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "playrunner": {
            "type": "http",
            "url": "https://playrunner.cloud/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http playrunner https://playrunner.cloud/mcp
```

## When to use it
- rerun browser checks after a code change
- find which tests failed in a workflow run
- inspect traces and screenshots from a failed run
- let CI start a saved Playwright workflow

## Example prompts
- Run the checkout smoke workflow once and tell me which tests passed or failed, with the report links.
- Find my Playrunner projects and create a workflow for the Playwright tests in this repository.
- Inspect the latest run and show its report, traces, and screenshots.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74569
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md