Skip to main content
Glama
enesjakozh
ThreatFlux

Playwright Fetch MCP Server

by ThreatFlux
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Playwright Fetch MCP サーバー

GitHub リリース（最新日付） CI コードコフ ライセンス: MIT Pythonバージョン 劇作家 MCP コードスタイル: 黒

Playwright を用いたブラウザ自動化のためのウェブコンテンツ取得機能を提供するモデルコンテキストプロトコル（LLM）サーバー。このサーバーにより、LLM はウェブページから JavaScript でレンダリングされたコンテンツを取得・処理し、HTML を Markdown に変換して利用しやすくすることができます。

著者

Claude Code の協力を得てWyatt Roersmaが作成しました。

Related MCP server: Playwright MCP Server for Security

主な特徴

  • ブラウザ自動化: Playwright を使用して、完全な JavaScript サポートを備えた Web ページをレンダリングします。

  • コンテンツ抽出: Webページから主要なコンテンツ領域を自動的に識別して抽出します

  • Markdown変換: HTMLをクリーンで読みやすいMarkdownに変換します

  • ページネーションサポート: ページネーションを通じて大きなコンテンツを処理します

  • robots.txt準拠: 自律的なフェッチのためのrobots.txtディレクティブを尊重

  • プロキシサポート: プロキシサーバー経由でリクエストをルーティングできます

  • Docker 対応: Docker HubおよびGitHub Container Registry経由でビルド済みの Docker イメージとして利用可能

利用可能なツール

  • playwright-fetch - Playwright ブラウザ自動化を使用して URL を取得し、その内容をマークダウンとして抽出します。

    • url (文字列、必須): 取得するURL

    • max_length （整数、オプション）：返される文字の最大数（デフォルト：5000）

    • start_index （整数、オプション）：この文字インデックスからコンテンツを開始します（デフォルト：0）

    • raw （ブール値、オプション）：マークダウン変換なしで生のコンテンツを取得します（デフォルト：false）

    • wait_for_js (ブール値、オプション): JavaScript の実行を待機します (デフォルト: true)

プロンプト

  • 劇作家フェッチ

    • Playwright を使用して URL を取得し、その内容をマークダウンとして抽出します。

    • 引数:

      • url (文字列、必須): 取得するURL

要件

  • Python 3.13.2以降

  • UVパッケージマネージャー

  • Playwrightブラウザがインストールされている

インストール

1. uvでインストールする（推奨）

uv pip install git+https://github.com/ThreatFlux/playwright-fetch.git
# Install Playwright browsers
uv pip exec playwright install

あるいは、リポジトリのクローンを作成してインストールします。

git clone https://github.com/ThreatFlux/playwright-fetch.git
cd playwright-fetch
uv pip install -e .
# Install Playwright browsers
uv pip exec playwright install

2. Dockerの使用

Docker Hub または GitHub Container Registry から、事前に構築された Docker イメージを使用できます。

# From Docker Hub
docker pull threatflux/playwright-fetch:latest

# From GitHub Container Registry
docker pull ghcr.io/threatflux/playwright-fetch:latest

または自分で構築します:

docker build -t threatflux/playwright-fetch .

構成

Claude.app 用に設定する

Claude 設定に追加:

"mcpServers": {
  "playwright-fetch": {
    "command": "uvx",
    "args": ["mcp-server-playwright-fetch"]
  }
}
"mcpServers": {
  "playwright-fetch": {
    "command": "docker",
    "args": ["run", "-i", "--rm", "threatflux/playwright-fetch"]
  }
}

VS Code用の設定

手動でインストールする場合は、VS Code のユーザー設定 (JSON) ファイルに次の JSON ブロックを追加します。

{
  "mcp": {
    "servers": {
      "playwright-fetch": {
        "command": "uvx",
        "args": ["mcp-server-playwright-fetch"]
      }
    }
  }
}
{
  "mcp": {
    "servers": {
      "playwright-fetch": {
        "command": "docker",
        "args": ["run", "-i", "--rm", "threatflux/playwright-fetch"]
      }
    }
  }
}

コマンドラインオプション

サーバーは次のコマンドライン オプションをサポートしています。

  • --user-agent : カスタムユーザーエージェント文字列

  • --ignore-robots-txt : robots.txt の制限を無視する

  • --proxy-url : リクエストに使用するプロキシ URL

  • --headless : ブラウザをヘッドレスモードで実行する (デフォルト: True)

  • --wait-until : ナビゲーションが成功したと見なすタイミング (選択肢: "load", "domcontentloaded", "networkidle", "commit"、デフォルト: "networkidle")

使用例

# Run with default settings
uv run mcp-server-playwright-fetch

# Run with a custom user agent and proxy
uv run mcp-server-playwright-fetch --user-agent="MyCustomAgent/1.0" --proxy-url="http://myproxy:8080"

# Run with visible browser for debugging
uv run mcp-server-playwright-fetch --headless=false

デバッグ

MCP インスペクタを使用してサーバーをデバッグできます。

npx @modelcontextprotocol/inspector uvx mcp-server-playwright-fetch

標準フェッチサーバーとの違い

この実装は、標準のフェッチ MCP サーバーとは次の点で異なります。

  1. ブラウザ自動化: Playwrightを使用してJavaScriptを多用したページをレンダリングします

  2. コンテンツ抽出: 一般的なページ構造からメインコンテンツを抽出します

  3. 待機オプション: 設定可能なページ読み込み戦略 (読み込み、DOM コンテンツ、ネットワークアイドルの待機)

  4. 表示ブラウザオプション: デバッグのために表示ブラウザで実行できます

ライセンス

このプロジェクトはMITライセンスの下で提供されています。詳細はLICENSEファイルをご覧ください。

Available Tools

1 tool
playwright-fetchC

Fetches a URL from the internet using Playwright and optionally extracts its contents as markdown. Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL to fetch
max_lengthNoMaximum number of characters to return.
start_indexNoOn return output starting at this character index, useful if a previous fetch was truncated and more context is required.
rawNoGet the actual HTML content of the requested page, without simplification.
wait_for_jsNoWait for JavaScript to execute (client-side rendering).

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions internet access and markdown extraction but fails to describe critical behaviors like rate limits, authentication needs, error handling, or what 'using Playwright' entails operationally. The description adds some context but is insufficient for a mutation-capable tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is verbose and unfocused, with redundant phrasing ('originally you did not have internet access, and were advised to refuse and tell the user this') and meta-commentary about agent capabilities. It lacks front-loading of key information, wasting space on historical context instead of tool functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 5 parameters, no annotations, and no output schema, the description is incomplete. It misses behavioral details like return format, error cases, and operational constraints. The emphasis on internet access history does not compensate for these gaps, leaving the agent under-informed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 5 parameters. The description adds no specific parameter semantics beyond implying markdown extraction relates to the 'raw' parameter. Baseline 3 is appropriate as the schema handles parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'fetches a URL from the internet using Playwright' and mentions optional markdown extraction, providing a specific verb ('fetches') and resource ('URL'). It distinguishes this as an internet access tool, though there are no sibling tools for comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by stating 'originally you did not have internet access... this tool now grants you internet access,' suggesting it should be used when internet access is needed. However, it lacks explicit guidance on when to use this tool versus alternatives or any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • First observedplaywright-fetch
Deploy Server
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clearly defined and distinct purpose.

Naming Consistency5/5

A single tool inherently has perfect naming consistency as there are no other tools to compare it against. The name 'playwright-fetch' follows a clear and descriptive pattern.

Tool Count2/5

One tool is too few for a server's apparent scope of internet fetching and content extraction. This minimal set feels thin and underdeveloped, lacking complementary tools like navigation, interaction, or data processing utilities that would enhance the domain coverage.

Completeness2/5

The tool surface is severely incomplete for the domain of web fetching and automation. While the single tool provides basic fetching and markdown extraction, there are significant gaps such as no navigation, form handling, screenshot capabilities, or data parsing tools that are typical in web automation contexts.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Related MCP Connectors

Related MCP Servers

  • Playwright MCP Server

    Sumitbhoyar
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides browser automation capabilities using Playwright, enabling users to navigate websites, extract content, take screenshots, and interact with web pages through natural language prompts.
    6 npm
    MIT

  • Playwright MCP Server for

    o0x1024
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables LLMs to perform browser automation tasks including web scraping, taking screenshots, and executing JavaScript using Playwright. It facilitates real-time interaction with web pages and the generation of automated test code.
    6 npm
    MIT

  • mcp-playwright

    ma-pony
    A
    license
    B
    quality
    D
    maintenance
    Provides browser automation capabilities for LLM applications, enabling web page interaction and data extraction via Playwright.
    12
    33 PyPI
    10
    MIT

  • Playwright MCP Server

    vinothbhc1986
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables browser automation using Playwright, allowing LLMs to interact with web pages, take screenshots, generate test code, scrape web pages, and execute JavaScript in a real browser environment.
    11,800 npm
    MIT

Appeared in Searches