Playrunner
Find Playwright workflows, start runs and read results in Playrunner Cloud from your agent
- Pricing
- Free trial
- Platforms
- Web, CLI, API
- Runs
- Remotely
- Version
- 0.1.1
- Listing updated
- 1 day ago
About Playrunner
Playrunner is an MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
The pitch is a safety net for code an AI agent has written. Instead of asking a model to reason through every browser step again, an agent starts a saved Playwright workflow by its ID, reads new run events without refetching earlier ones, and opens the report, trace or video only when it needs to investigate. Failures return the failing step, expected result and captured evidence, and run history is kept so a later conversation or teammate can pick up where the last one stopped.
Workflows combine an existing Playwright test or inline script with an environment, an optional authentication profile and a place to run. They can also be started from a visual editor, the CLI or a schedule. The README lists Codex, Claude, Cursor, Gemini CLI, Antigravity and Grok as clients, and asks for remote Streamable HTTP with OAuth or a shell-capable agent using the CLI.
Playrunner can be self-hosted under its Sustainable Use License, which is source-available rather than open source and forbids selling it or offering a service built on it. Cloud costs $30 a month with 2,000 credits, a 14-day trial with 200 credits, and usage-based credits for orchestration and runner compute.
Install
Run in a terminal
claude mcp add --transport http mcp https://playrunner.cloud/mcpAdd to Settings → Connectors → Add custom connector
https://playrunner.cloud/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://playrunner.cloud/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://playrunner.cloud/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"serverUrl": "https://playrunner.cloud/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://playrunner.cloud/mcp"
}
}
}What it does
- Saved test workflows
- Turn Playwright tests into reusable workflows an agent can start by ID.
- Evidence-first results
- Returns failing step, expected result, logs, traces, screenshots and video.
- Incremental run events
- Agents read only new events since their last check.
- Environments and sign-ins
- Reuse environments and authentication profiles across runs.
- Run history
- Earlier failures and later runs stay available across conversations.
- Self-host or Cloud
- Run locally under the source-available license or use managed orchestration.
Good for
- Have an agent run a checkout smoke test after each change
- Investigate a failing booking flow using traces and screenshots
- Check that a two-way customer sync creates no duplicates
- Share test evidence with QA and release owners
Pricing
Free trial, from $30 a month
Self-host free for permitted use; Cloud $30/month with 14-day trial and 200 credits
Prices change. Check playrunner.dev before you buy.
Playrunner FAQ
Is Playrunner open source?
No. It is source-available under the Playrunner Sustainable Use License, which is not OSI-approved.
What does Cloud cost?
$30 a month before tax with 2,000 credits, plus $10 per 1,000 extra credits.
Can I use my own runners?
Yes. Own runners avoid the compute charge, but hosted orchestration still uses 0.25 credits per minute.
Which agents work with it?
Codex, Claude, Cursor, Gemini CLI, Antigravity and Grok are listed.
Is Playrunner free?
Playrunner is a paid product with a free trial. Paid plans start at $30 a month.
How do I add Playrunner to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp https://playrunner.cloud/mcp
What are the best alternatives to Playrunner?
The closest alternatives to Playrunner are REA, Browser Use, Scrapling MCP Server, Codebase Memory and GitHub.
Alternatives to Playrunner

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Browser Use
MCP serverBrowser agents and cloud browsers for AI, with an MCP server for web tasks
- 7 tools
- Remote
- Freemium
- 121K GitHub stars
- Browser automation

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools