Playwright Fetch MCP Server
@ThreatFlux
About Playwright Fetch MCP Server
A fetch mcp server
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"playwright-fetch": {
"command": "uv",
"args": [
"pip",
"install",
"git+https://github.com/ThreatFlux/playwright-fetch.git"
]
}
}
}Tools
1Fetches a URL using Playwright browser automation and extracts its contents as markdown.
Overview
What is Playwright Fetch MCP Server?
A Model Context Protocol server that uses Playwright browser automation to fetch and extract JavaScript-rendered web content. It converts HTML to clean markdown for easier consumption by large language models. Created by Wyatt Roersma.
How to use Playwright Fetch MCP Server?
Install via uv or Docker, then configure it as an MCP server in your client (e.g., Claude.app or VS Code). Use the playwright-fetch tool with a required url argument and optional parameters like max_length, start_index, raw, and wait_for_js.
Key features of Playwright Fetch MCP Server
- Full browser automation with Playwright for JavaScript rendering
- Automatic identification and extraction of main content areas
- Conversion of HTML to clean, readable markdown
- Supports pagination for large content
- Respects
robots.txtdirectives (configurable) - Proxy support via
--proxy-urlcommand-line option - Available as a pre-built Docker image
Use cases of Playwright Fetch MCP Server
- Fetching content from modern single-page applications (SPAs)
- Extracting readable text from JavaScript-heavy documentation sites
- Automating web research for LLM applications requiring rendered page data
- Testing and debugging web scraping workflows with a visible browser option
FAQ from Playwright Fetch MCP Server
What makes this server different from the standard fetch MCP server?
It uses Playwright for browser automation, can render JavaScript-heavy pages, attempts to extract main content from common page structures, and offers configurable page loading strategies (e.g., networkidle, domcontentloaded). It can also run with a visible browser for debugging.
What are the runtime requirements?
Python 3.13.2 or newer, the uv package manager, and Playwright browsers installed. A pre-built Docker image is also available for containerized environments.
How do I install Playwright Fetch MCP Server?
Install via uv: uv pip install git+https://github.com/ThreatFlux/playwright-fetch.git then run uv pip exec playwright install. Or use the Docker image: docker pull threatflux/playwright-fetch.
How do I configure it for Claude.app or VS Code?
Add the server to your MCP configuration. For uvx, use: { "command": "uvx", "args": ["mcp-server-playwright-fetch"] }. For Docker, use: { "command": "docker", "args": ["run", "-i", "--rm", "threatflux/playwright-fetch"] }.
Can I set a custom user agent or proxy?
Yes. Use command-line options --user-agent, --proxy-url, --ignore-robots-txt, --headless, and --wait-until when starting the server.
Frequently asked questions
What makes this server different from the standard fetch MCP server?
It uses Playwright for browser automation, can render JavaScript-heavy pages, attempts to extract main content from common page structures, and offers configurable page loading strategies (e.g., `networkidle`, `domcontentloaded`). It can also run with a visible browser for debugging.
What are the runtime requirements?
Python 3.13.2 or newer, the `uv` package manager, and Playwright browsers installed. A pre-built Docker image is also available for containerized environments.
How do I install Playwright Fetch MCP Server?
Install via `uv`: `uv pip install git+https://github.com/ThreatFlux/playwright-fetch.git` then run `uv pip exec playwright install`. Or use the Docker image: `docker pull threatflux/playwright-fetch`.
How do I configure it for Claude.app or VS Code?
Add the server to your MCP configuration. For `uvx`, use: `{ "command": "uvx", "args": ["mcp-server-playwright-fetch"] }`. For Docker, use: `{ "command": "docker", "args": ["run", "-i", "--rm", "threatflux/playwright-fetch"] }`.
Can I set a custom user agent or proxy?
Yes. Use command-line options `--user-agent`, `--proxy-url`, `--ignore-robots-txt`, `--headless`, and `--wait-until` when starting the server.
Basic information
More Browser Automation MCP servers
Webpage Screenshot MCP Server
ananddtyagiAn MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.
browser-use-mcp-server
co-browserBrowse the web, directly from Cursor etc.
playwright-server MCP server
blackwhite084X Twitter Scraper
Xquik-devTwitter scraper API skill for tweet search, advanced Twitter search, profile tweets, follower export, media download, monitors, webhooks, MCP, and posting automation: send tweets and replies.
Scrapling Fetch MCP
cyberchittaHelps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.
Comments