MCP Server Fetch TypeScript
Servidor MCP mcp-server-fetch-typescript
Un servidor de Protocolo de Contexto de Modelo que proporciona capacidades de obtención y conversión de contenido web. Este servidor implementa un sistema integral de recuperación de contenido web compatible con diversos formatos y métodos de renderizado, lo que lo hace ideal para tareas que abarcan desde la extracción simple de datos hasta el raspado web sofisticado.
Características
Herramientas
get_raw_text- Recupera contenido de texto sin procesar directamente de las URLToma
urlcomo un parámetro obligatorio que apunta a recursos basados en textoDevuelve contenido de texto sin procesar sin renderizar en el navegador
Ideal para archivos JSON, XML, CSV, TSV o de texto sin formato
Se utiliza mejor cuando se necesita acceso rápido y directo al contenido fuente.
get_rendered_html- Obtener contenido HTML completamente renderizadoToma
urlcomo parámetro obligatorioDevuelve contenido HTML completo después de la ejecución de JavaScript
Utiliza Playwright para la renderización sin interfaz gráfica del navegador
Esencial para aplicaciones web modernas y SPA
get_markdown- Convertir contenido web al formato MarkdownToma
urlcomo parámetro obligatorioDevuelve Markdown bien formateado que conserva los elementos estructurales
Admite tablas y listas de definiciones
Recomendado para archivar y documentar contenidos.
get_markdown_summary- Extraer y convertir el contenido principalToma
urlcomo parámetro obligatorioDevuelve Markdown limpio centrándose en el contenido principal
Elimina automáticamente la navegación, los encabezados y los pies de página.
Perfecto para la extracción de artículos y publicaciones de blogs.
Related MCP server: MCP Server for Google Search
Instalación
Como paquete global
npm install -g mcp-server-fetch-typescriptComo dependencia del proyecto
npm install mcp-server-fetch-typescriptUso
Uso con Claude Desktop
Para utilizar con Claude Desktop, agregue la configuración del servidor:
En MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
En Windows: %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"mcp-server-fetch-typescript": {
"command": "npx",
"args": [
"-y",
"mcp-server-fetch-typescript"
]
}
}o agregue la siguiente configuración:
git clone https://github.com/tatn/mcp-server-fetch-typescript.git
cd mcp-server-fetch-typescript
npm install
npm run build"mcpServers": {
"mcp-server-fetch-typescript": {
"command": "node",
"args": [
"/path/to/mcp-server-fetch-typescript/build/index.js"
]
}
}Depuración
Para depurar el servidor MCP:
npx @modelcontextprotocol/inspector npx -y mcp-server-fetch-typescriptnpx @modelcontextprotocol/inspector node /path/to/mcp-server-fetch-typescript/build/index.jsAvailable Tools
4 toolsget_markdownA
Converts web page content to well-formatted Markdown, preserving structural elements like tables and definition lists. Recommended as the default tool for web content extraction when a clean, readable text format is needed while maintaining document structure.
Inputs: url (required).
get_markdown_summaryA
Extracts and converts the main content area of a web page to Markdown format, automatically removing navigation menus, headers, footers, and other peripheral content. Perfect for capturing the core content of articles, blog posts, or documentation pages.
Inputs: url (required).
get_raw_textA
Retrieves raw text content directly from a URL without browser rendering. Ideal for structured data formats like JSON, XML, CSV, TSV, or plain text files. Best used when fast, direct access to the source content is needed without processing dynamic elements.
Inputs: url (required).
get_rendered_htmlA
Fetches fully rendered HTML content using a headless browser, including JavaScript-generated content. Essential for modern web applications, single-page applications (SPAs), or any content that requires client-side rendering to be complete.
Inputs: url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: get_markdown preserves full structure, get_markdown_summary focuses on core content, get_raw_text handles raw data formats, and get_rendered_html captures JavaScript-rendered content. The descriptions explicitly differentiate use cases, leaving no ambiguity for agent selection.
All tool names follow a consistent 'get_*' verb_noun pattern with snake_case, making them predictable and easy to parse. The naming convention is uniform across all four tools, enhancing readability and coherence.
With 4 tools, the set is well-scoped for a web content fetching server, covering key extraction methods (Markdown, raw text, rendered HTML) and a specialized summary variant. Each tool earns its place without redundancy or excessive complexity.
The tool surface comprehensively covers the domain of web content fetching: it includes raw extraction, rendered content, and two Markdown variants for different needs. There are no obvious gaps, as the tools handle static, dynamic, and structured content effectively.
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
Model Context Protocol server for Studex tools, notifications, and profile integrations
A remote MCP server to convert HTML documents (URL or raw source) to PDF or screenshots
MCP server for web extraction and rendering via AceDataCloud WebExtrator
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that converts Markdown content to HTML format.14,207 npm2MIT
- FlicenseAqualityCmaintenanceA Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.26 npm2-
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.2MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing web search capabilities using Google Custom Search API and webpage content extraction functionality.2MIT