Skip to main content
Glama
enesjakozh
wolfyy970

Docs Fetch MCP Server

by wolfyy970
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Servidor MCP de obtención de documentos

Un servidor de Protocolo de Contexto de Modelo (MCP) para obtener contenido web con capacidades de exploración recursiva. Este servidor permite a los LLM explorar de forma autónoma páginas web y documentación para aprender sobre temas específicos.

Descripción general

El servidor MCP Docs Fetch ofrece a los LLM una forma sencilla pero eficaz de recuperar y explorar contenido web. Permite:

  • Obtener contenido limpio y legible de cualquier página web

  • Exploración recursiva de páginas vinculadas hasta una profundidad especificada

  • Recorrido de enlaces del mismo dominio para recopilar información completa

  • Filtrado inteligente de enlaces de navegación para centrarse en páginas con mucho contenido

Esta herramienta es particularmente útil cuando los usuarios desean que un LLM aprenda sobre un tema específico explorando documentación o contenido web.

Related MCP server: Spider MCP Server

Características

  • Extracción de contenido : extrae de forma limpia el contenido principal de las páginas web, eliminando distracciones como navegación, anuncios y elementos irrelevantes.

  • Análisis de enlaces : identifica y extrae enlaces de la página, evaluando su relevancia

  • Exploración recursiva : sigue enlaces a contenido relacionado dentro del mismo dominio, hasta una profundidad especificada

  • Procesamiento paralelo : rastrea contenido de manera eficiente con solicitudes simultáneas y manejo adecuado de errores

  • Manejo robusto de errores : maneja con elegancia problemas de red, tiempos de espera y páginas malformadas.

  • Enfoque de doble estrategia : utiliza primero solicitudes rápidas de Axios y, como alternativa, Puppetteer para páginas más complejas.

  • Prevención de tiempo de espera : implementa el manejo de tiempo de espera global para garantizar un funcionamiento confiable dentro de los límites de tiempo de MCP

  • Resultados parciales : devuelve el contenido disponible incluso cuando algunas páginas no se cargan por completo

Uso

El servidor expone una única herramienta MCP:

fetch_doc_content

Obtiene contenido de páginas web con la capacidad de explorar páginas vinculadas hasta una profundidad específica.

Parámetros:

  • url (cadena, obligatoria): URL de la página web que se va a buscar

  • depth (número, opcional, predeterminado: 1): profundidad máxima de exploración de directorios/enlaces (1-5)

Devoluciones:

{
  "rootUrl": "https://example.com/docs",
  "explorationDepth": 2,
  "pagesExplored": 5,
  "content": [
    {
      "url": "https://example.com/docs",
      "title": "Documentation",
      "content": "Main page content...",
      "links": [
        {
          "url": "https://example.com/docs/topic1",
          "text": "Topic 1"
        },
        ...
      ]
    },
    ...
  ]
}

Instalación

  1. Clonar este repositorio:

git clone https://github.com/wolfyy970/docs-fetch-mcp.git
cd docs-fetch-mcp

  1. Instalar dependencias:

npm install

  1. Construir el proyecto:

npm run build

  1. Configure los ajustes de MCP en su cliente Claude:

{
  "mcpServers": {
    "docs-fetch": {
      "command": "node",
      "args": [
        "/path/to/docs-fetch-mcp/build/index.js"
      ],
      "env": {
        "MCP_TRANSPORT": "pipe"
      }
    }
  }
}

Dependencias

  • @modelcontextprotocol/sdk : SDK del servidor MCP

  • puppeteer : Navegador sin cabeza para la interacción con páginas web

  • axios : cliente HTTP para realizar solicitudes

Desarrollo

Para ejecutar el servidor en modo de desarrollo:

npm run dev

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

1 tool
fetch_doc_contentC

Fetch web page content with the ability to explore linked pages up to a specified depth

NameRequiredDescriptionDefault
depthNoMaximum depth of directory/link exploration (default: 1)
urlYesURL of the web page to fetch

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the core functionality (fetching and exploring links) but lacks details on permissions, rate limits, error handling, or what the response looks like (e.g., format, size limits). This leaves significant gaps for a tool that interacts with external web resources.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that clearly states the tool's purpose and key feature (exploring linked pages). It is front-loaded with the main action and includes no redundant information, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of fetching web content with link exploration, no annotations, and no output schema, the description is incomplete. It doesn't cover behavioral aspects like authentication needs, rate limits, or response format, which are critical for effective tool use in this context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the schema already documents both parameters ('url' and 'depth') with descriptions and constraints. The description adds minimal value by implying the depth parameter relates to link exploration, but it doesn't provide additional syntax or format details beyond what the schema specifies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('fetch') and resource ('web page content'), and it adds valuable context about exploring linked pages. However, since there are no sibling tools mentioned, it doesn't need to differentiate from alternatives, which keeps it from reaching a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or exclusions. It mentions the ability to explore linked pages up to a specified depth, but this is more about functionality than usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedfetch_doc_content
Deploy Server
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'fetch_doc_content' has a clear and distinct purpose, making it impossible for an agent to confuse it with other tools.

Naming Consistency5/5

Since there is only one tool, it inherently follows a consistent naming pattern. The tool name 'fetch_doc_content' uses a verb_noun structure, which is clear and predictable, and there are no other tools to cause inconsistency.

Tool Count2/5

A single tool is too few for a server named 'Docs Fetch MCP Server', which implies a domain involving document fetching and exploration. While the tool is well-described, one tool feels thin and insufficient for comprehensive operations like managing fetched content or handling different document types, limiting the server's utility.

Completeness2/5

The tool surface is severely incomplete for the inferred domain of document fetching. It only provides a fetch operation with depth control, missing essential functions such as listing fetched documents, updating or deleting cached content, searching within documents, or handling errors, which are necessary for a complete workflow.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Crawl4AI RAG MCP Server

    Chillbruhhh
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents and coding assistants with advanced web crawling and RAG capabilities, allowing them to scrape websites and leverage that knowledge through various retrieval strategies.
    2
    MIT

  • Spider MCP Server

    oeo
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables crawling and extracting clean content from documentation websites with optional LLM-powered analysis for intelligent summaries, code example extraction, and content classification.
    -

  • Fetch MCP Server

    MaartenSmeets
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables LLMs to fetch and extract web content using browser automation, OCR, and multiple extraction methods, handling JavaScript rendering and anti-scraping techniques.
    17
    MIT

Appeared in Searches