# Playwrightess (Playwright)

> Use this tool when you need to automate complex browser interactions with stateful sessions, such as multi-step web scraping or testing scenarios. It provides a persistent Playwright evaluation environment, maintaining browser, context, and page state between JavaScript code executions, with inputs of JavaScript code and outputs of execution results and console logs. Ideal for use cases requiring session management and variable tracking across multiple browser actions.

Canonical page: https://skillsregistry.net/skills/mitsuhiko-playwrightess  
JSON: https://api.skillsregistry.net/v1/skills/mitsuhiko-playwrightess

## Description

Playwrightess MCP provides a persistent Playwright evaluation environment through a single `playwright_eval` tool that maintains browser, context, and page state between JavaScript code executions. Unlike traditional Playwright MCP implementations that expose individual browser actions as separate tools, this experimental approach offers a JavaScript programming interface where variables like browser, context, and page persist across evaluations while other local variables are reset. Built with session management using persistent browser contexts, AST-based code rewriting for variable tracking, and comprehensive console logging capture, it enables AI agents to write complex browser automation workflows using the full Playwright API with stateful interactions, making it valuable for multi-step web scraping, testing scenarios, or interactive web application workflows that require maintaining session state.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mitsuhiko-playwrightess)
- **Repository:** <https://github.com/mitsuhiko/playwrightess-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mitsuhiko-playwrightess"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mitsuhiko-playwrightess` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mitsuhiko-playwrightess/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt