Loading...
Fetcher MCP retrieves web page content using Playwright, supporting JavaScript execution, content extraction, and flexible output formats, enabling dynamic web scraping.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
Fetcher MCP retrieves web page content using Playwright, supporting JavaScript execution, content extraction, and flexible output formats, enabling dynamic web scraping.
Fetcher MCP is relatively safe for read operations, but the ability to execute JavaScript from fetched web pages introduces potential risks. It's crucial to sanitize inputs and monitor resource usage to mitigate potential security vulnerabilities. Running it in a sandboxed environment is recommended.
Performance depends on network conditions and website complexity. Parallel fetching can improve throughput, but may also increase resource consumption.
Cost depends on resource usage (CPU, memory, bandwidth). Consider the cost of running Playwright and the potential for increased network traffic.
npx -y fetcher-mcp{
"mcpServers": {
"fetcher": {
"command": "npx",
"args": ["-y", "fetcher-mcp"]
}
}
}NODE_ENVfetch_urlRetrieves web page content from a specified URL using Playwright.
Executes JavaScript and fetches content from arbitrary URLs.
fetch_urlsBatch retrieves web page content from multiple URLs in parallel.
Parallel fetching increases the risk of resource exhaustion and potential abuse.
browser_installInstalls the Playwright Chromium browser binary automatically.
Installs binaries, potentially introducing malicious software if the source is compromised.
None
cloud
Fetcher MCP is relatively safe for read operations, but the ability to execute JavaScript from fetched web pages introduces potential risks. It's crucial to sanitize inputs and monitor resource usage to mitigate potential security vulnerabilities. Running it in a sandboxed environment is recommended.
Autonomy is limited by the tool's capabilities. Sandboxing through Docker or similar technologies is recommended to mitigate risks.
Production Tip
Implement rate limiting and input validation to prevent abuse and ensure stability in production environments.
Use the `waitForNavigation` parameter and increase the `timeout` to allow the page to fully load.
Set `extractContent` to `false` and `returnHtml` to `true`.
Run the server with the `--debug` flag or set `debug: true` for a specific request.
Yes, enable debug mode and manually log in to the website in the opened browser window.
Run `npx playwright install chromium` in your terminal.
Both HTML and Markdown are supported.
Use the `fetch_urls` tool for parallel fetching of multiple URLs.