広告掲載
MCP.so
ログイン

Playwright Sse MCP Server

@torohash

リポジトリ

基本情報

カテゴリ

ブラウザ自動化

トランスポート

stdio

作者

torohash

Playwright Sse MCP Server について

playwright/mcpをsseで外部から触るためのやつ

#mcp

Playwright Sse MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "playwright-sse-mcp-server": {
      "command": "docker",
      "args": [
        "network",
        "create",
        "mcp-network"
      ]
    }
  }
}

Playwright Sse MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is playwright-sse-mcp-server?

playwright-sse-mcp-server provides Playwright as an MCP (Model Context Protocol) server, enabling MCP clients to use Playwright’s browser automation features. It runs inside a Docker container and is intended for developers who need browser control from MCP-compatible tools.

How to use playwright-sse-mcp-server?

Clone the repository and run docker compose up --build in the project root. The server starts on port 3002 by default; set the PORT environment variable for a custom port. Connect from other containers on the same Docker network via playwright-sse-mcp-server:<PORT>/sse, or from the host via localhost:<PORT>/sse. For Roo Code, configure the MCP settings with the SSE URL. Helper shell scripts (playwright-mcp-start, playwright-mcp-stop, playwright-mcp-logs) are provided for convenient control.

Key features of playwright-sse-mcp-server

  • Playwright browser automation exposed via MCP SSE transport
  • Docker‑based deployment with configurable port (default 3002)
  • Connects from same Docker network, host, or development containers
  • Shell scripts for start/stop/logs with persistent mode and restart policies
  • Requires a pre‑existing Docker network named mcp-network

Use cases of playwright-sse-mcp-server

  • Use an MCP client like Roo Code to automate browser tasks
  • Run headless Playwright inside a container for testing or scraping
  • Integrate browser automation into MCP‑based workflows

よくある質問

1

What are the prerequisites for running the server?

Docker and docker‑compose must be installed. A Docker network named `mcp-network` must exist; if not, create it with `docker network create mcp-network`.

2

How do I connect from a development container not on `mcp-network`?

Use the host IP or special DNS name. On Docker Desktop (Mac/Windows) use `host.docker.internal:<PORT>/sse`. On Linux, use the host’s IP or the Docker bridge gateway (e.g., `172.17.0.1`). The port must match the one published in `compose.yml`.

3

Does Cline support this server?

As of 2025/03/27, Cline does not support SSE, so it cannot be used with this server.

4

Can I change the default port?

Yes, set the environment variable `PORT` before starting the server. For example: `PORT=4000 docker compose up --build`.

5

What mode does Playwright run in?

The server runs Playwright in headless mode.

コメント

「ブラウザ自動化」の他のコンテンツ

Nullprint

nullprintai

Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.

Scrapling Fetch MCP

cyberchitta

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

101

Screenshot Scout

screenshotscout

Capture screenshots of webpages as images or PDFs with Screenshot Scout.

Firecrawl Mcp Server

mendableai

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

6.9K

Puppeteer MCP Server

merajmehrabi

This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.

474
広告掲載