A server that allows fetching web page content using Playwright headless browser with AI-powered capabilities for efficient information extraction.
Welcome to the Fetcher MCP GitHub repository! This repository hosts the MCP server for fetching web page content using the Playwright headless browser.
The Fetcher MCP is designed to leverage artificial intelligence capabilities to efficiently retrieve web page content. By utilizing the Playwright headless browser, this server can navigate through web pages and extract desired information with ease.
? AI-Powered Content Fetching
? Playwright Integration
? Fast and Efficient
? Easy Setup and Configuration
You can download the latest version of the Fetcher MCP server from the following link:
Note:The provided link leads directly to the application file. Please make sure to launch the application after downloading.
If the link is not accessible or does not work, you can check the "Releases" section of this repository for alternative download options.
To start using the Fetcher MCP server for content fetching, follow these simple steps:
For more information, resources, or support regarding the Fetcher MCP server, feel free to visit the official website at https://github.com/everford/fetcher-mcp/releases.
We welcome contributions to enhance the Fetcher MCP server and make it even more powerful and efficient. If you have any ideas, suggestions, or improvements, please submit a pull request following our guidelines.
Connect with other developers, share insights, and stay updated on the latest news related to the Fetcher MCP server by joining our community:
? Slack Channel
? Twitter
? Newsletter
? Start using the Fetcher MCP server today for seamless web page content fetching with AI-powered capabilities. Effortlessly extract the information you need using the Playwright headless browser integration. Happy Fetching! ?
Remember, the Fetcher MCP server simplifies the process of web page content retrieval, making it faster and more efficient than ever before. Download the latest version now and experience the power of AI and Playwright in action. Happy fetching! ?
[
{
"description": "Retrieve web page content from a specified URL",
"inputSchema": {
"properties": {
"debug": {
"description": "Whether to enable debug mode (showing browser window), overrides the --debug command line flag if specified",
"type": "boolean"
},
"disableMedia": {
"description": "Whether to disable media resources (images, stylesheets, fonts, media), default is true",
"type": "boolean"
},
"extractContent": {
"description": "Whether to intelligently extract the main content, default is true",
"type": "boolean"
},
"maxLength": {
"description": "Maximum length of returned content (in characters), default is no limit",
"type": "number"
},
"navigationTimeout": {
"description": "Maximum time to wait for additional navigation in milliseconds, default is 10000 (10 seconds)",
"type": "number"
},
"returnHtml": {
"description": "Whether to return HTML content instead of Markdown, default is false",
"type": "boolean"
},
"timeout": {
"description": "Page loading timeout in milliseconds, default is 30000 (30 seconds)",
"type": "number"
},
"url": {
"description": "URL to fetch",
"type": "string"
},
"waitForNavigation": {
"description": "Whether to wait for additional navigation after initial page load (useful for sites with anti-bot verification), default is false",
"type": "boolean"
},
"waitUntil": {
"description": "Specifies when navigation is considered complete, options: 'load', 'domcontentloaded', 'networkidle', 'commit', default is 'load'",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "fetch_url"
},
{
"description": "Retrieve web page content from multiple specified URLs",
"inputSchema": {
"properties": {
"debug": {
"description": "Whether to enable debug mode (showing browser window), overrides the --debug command line flag if specified",
"type": "boolean"
},
"disableMedia": {
"description": "Whether to disable media resources (images, stylesheets, fonts, media), default is true",
"type": "boolean"
},
"extractContent": {
"description": "Whether to intelligently extract the main content, default is true",
"type": "boolean"
},
"maxLength": {
"description": "Maximum length of returned content (in characters), default is no limit",
"type": "number"
},
"navigationTimeout": {
"description": "Maximum time to wait for additional navigation in milliseconds, default is 10000 (10 seconds)",
"type": "number"
},
"returnHtml": {
"description": "Whether to return HTML content instead of Markdown, default is false",
"type": "boolean"
},
"timeout": {
"description": "Page loading timeout in milliseconds, default is 30000 (30 seconds)",
"type": "number"
},
"urls": {
"description": "Array of URLs to fetch",
"items": {
"type": "string"
},
"type": "array"
},
"waitForNavigation": {
"description": "Whether to wait for additional navigation after initial page load (useful for sites with anti-bot verification), default is false",
"type": "boolean"
},
"waitUntil": {
"description": "Specifies when navigation is considered complete, options: 'load', 'domcontentloaded', 'networkidle', 'commit', default is 'load'",
"type": "string"
}
},
"required": [
"urls"
],
"type": "object"
},
"name": "fetch_urls"
}
]