This server allows you to fetch web content using Playwright for browser automation with the following capabilities:
- Fetch URLs: Retrieve content from any web page with full JavaScript rendering support
- Content Extraction: Extract main content and convert to clean, readable markdown
- Raw HTML Option: Get unmodified HTML content when needed
- Content Management: Control character limits and use pagination with start index parameters
- JavaScript Support: Wait for client-side rendering to complete for accurate content
- Request Customization: Configure user-agent strings and proxy URLs
- Compliance Controls: Respect or bypass robots.txt directives as needed
- Debugging Features: Run with visible browser for troubleshooting
- Internet Access: Provides web content retrieval capabilities for LLMs
Integrates with Codecov for code coverage reporting and tracking through CI/CD workflows.
Offers pre-built Docker images available through Docker Hub and GitHub Container Registry for containerized deployment.
Enables integration with GitHub through container registry support and CI/CD workflows.
Handles JavaScript-rendered content from web pages, specifically waiting for JavaScript execution to complete before processing content.
Converts fetched HTML content to clean, readable markdown format for easier consumption by language models.
Built for Python 3.13+ environments, providing a Python-based implementation of the web content fetching capabilities.
Playwright Fetch MCP Server
A Model Context Protocol server that provides web content fetching capabilities using Playwright for browser automation. This server enables LLMs to retrieve and process JavaScript-rendered content from web pages, converting HTML to markdown for easier consumption.
Author
Created by Wyatt Roersma with assistance from Claude Code.
Key Features
- Browser Automation: Uses Playwright to render web pages with full JavaScript support
- Content Extraction: Automatically identifies and extracts main content areas from web pages
- Markdown Conversion: Converts HTML to clean, readable markdown
- Pagination Support: Handles large content through pagination
- Robots.txt Compliance: Respects robots.txt directives for autonomous fetching
- Proxy Support: Allows routing requests through a proxy server
- Docker Ready: Available as pre-built Docker images via Docker Hub and GitHub Container Registry
Available Tools
playwright-fetch
- Fetches a URL using Playwright browser automation and extracts its contents as markdown.url
(string, required): URL to fetchmax_length
(integer, optional): Maximum number of characters to return (default: 5000)start_index
(integer, optional): Start content from this character index (default: 0)raw
(boolean, optional): Get raw content without markdown conversion (default: false)wait_for_js
(boolean, optional): Wait for JavaScript to execute (default: true)
Prompts
- playwright-fetch
- Fetch a URL using Playwright and extract its contents as markdown
- Arguments:
url
(string, required): URL to fetch
Requirements
- Python 3.13.2 or newer
- uv package manager
- Playwright browsers installed
Installation
1. Install with uv (recommended)
Alternatively, clone the repository and install:
2. Using Docker
You can use our pre-built Docker images from Docker Hub or GitHub Container Registry:
Or build it yourself:
Configuration
Configure for Claude.app
Add to your Claude settings:
Configure for VS Code
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code.
Command Line Options
The server supports these command-line options:
--user-agent
: Custom User-Agent string--ignore-robots-txt
: Ignore robots.txt restrictions--proxy-url
: Proxy URL to use for requests--headless
: Run browser in headless mode (default: True)--wait-until
: When to consider navigation succeeded (choices: "load", "domcontentloaded", "networkidle", "commit", default: "networkidle")
Example Usage
Debugging
You can use the MCP inspector to debug the server:
Differences from Standard Fetch Server
This implementation differs from the standard fetch MCP server in these ways:
- Browser Automation: Uses Playwright to render JavaScript-heavy pages
- Content Extraction: Attempts to extract main content from common page structures
- Wait Options: Configurable page loading strategy (wait for load, DOM content, network idle)
- Visible Browser Option: Can run with a visible browser for debugging
License
This project is licensed under the MIT License. See the LICENSE file for details.
You must be authenticated.
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Tools
Provides web content fetching capabilities using Playwright browser automation, enabling LLMs to retrieve and process JavaScript-rendered content from web pages and convert HTML to markdown for easier consumption.
- Author
- Key Features
- Available Tools
- Prompts
- Requirements
- Installation
- Configuration
- Command Line Options
- Example Usage
- Debugging
- Differences from Standard Fetch Server
- License
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityThis server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.Last updated -148,131JavaScriptMIT License
- AsecurityAlicenseAqualityA Model Context Protocol server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.Last updated -1318,1153,496TypeScriptMIT License
- AsecurityFlicenseAqualityA server that enables browser automation using Playwright, allowing interaction with web pages, capturing screenshots, and executing JavaScript in a browser environment through LLMs.Last updated -1218,1151TypeScript
- AsecurityFlicenseAqualityEnables LLMs to perform browser automation through the Playwright framework with Chrome DevTools Protocol support, connecting to existing Chrome instances for advanced web interactions and JavaScript execution.Last updated -129TypeScript