A
licenseB
qualityD
maintenanceA Model Context Protocol server that enables LLMs to perform web searches using Google's Custom Search API through a standardized interface.
1
47
MIT
Scrapeless MCP Server
Servidor Mcp sin raspado
El Protocolo de Contexto de Modelo (MCP) es un protocolo abierto que permite una integración fluida entre las aplicaciones LLM y las fuentes de datos y herramientas externas. MCP proporciona una forma estandarizada de conectar LLM con el contexto requerido, lo que ayuda a optimizar eficientemente las interfaces de chat, crear IDE basados en IA o crear flujos de trabajo de IA personalizados.
Integre fácilmente los resultados de las SERP de Google (Búsqueda de Google, Google Flight, Google Maps, Google Jobs, etc.) en tiempo real en sus aplicaciones LLM mediante el servidor MCP de Scrapeless. Este servidor actúa como puente entre las LLM (como ChatGPT, Claude, etc.) y las SERP de Google de Scrapeless, lo que permite la recuperación dinámica de contexto para flujos de trabajo de IA, chatbots y herramientas de investigación.
👉 Punto final MCP en vivo:
📦 Paquete NPM: scrapeless-mcp-server
Descripción general
Este proyecto proporciona varios servidores MCP que permiten a los asistentes de IA como Claude realizar diversas operaciones de búsqueda y recuperar datos de:
Búsqueda de Google
Related MCP server: MCP Web Research Server
Herramientas
1. Herramienta de búsqueda
Nombre:
google-searchDescripción: Busque en la web usando Scrapeless
Parámetros:
query(obligatoria): El parámetro define la consulta que desea buscar. Puede usar cualquier término que usaría en una búsqueda normal de Google, por ejemplo, inurl:, site:, intitle:.gl(opcional, valor predeterminado: "us"): Este parámetro define el país que se usará en la búsqueda de Google. Es un código de país de dos letras (p. ej., "us" para Estados Unidos, "uk" para el Reino Unido o "fr" para Francia).hl(opcional, predeterminado: "en"): Este parámetro define el idioma que se usará en la búsqueda de Google. Es un código de idioma de dos letras (p. ej., "en" para inglés, "es" para español o "fr" para francés).
Guía de configuración
1. Obtenga una clave sin raspaduras
Regístrate en Scrapeless
2. Configurar
{
"mcpServers": {
"scrapelessMcpServer": {
"command": "npx",
"args": ["-y", "scrapeless-mcp-server"],
"env": {
"SCRAPELESS_KEY": "YOUR_SCRAPELESS_KEY"
}
}
}
}Consultas de ejemplo
A continuación se muestran algunos ejemplos de cómo utilizar estos servidores con Claude Desktop:
Búsqueda de Google
Please search for "climate change solutions" and summarize the top results.Instalación
Prerrequisitos
Node.js 22 o superior
NPM o Hilo
Instalar desde la fuente
Clonar el repositorio:
git clone https://github.com/scrapeless-ai/scrapeless-mcp-server.git
cd scrapeless-mcp-serverInstalar dependencias:
npm installConstruir el servidor:
npm run buildComunidad
Available Tools
1 toolgoogle-searchCInspect
Fetch Google Search Results
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| gl | No | Parameter defines the country to use for the Google search. It's a two-letter country code. (e.g., us for the United States, uk for United Kingdom, or fr for France). | |
| hl | No | Parameter defines the language to use for the Google search. It's a two-letter language code. (e.g., en for English, es for Spanish, or fr for French). | |
| query | Yes | Parameter defines the query you want to search. You can use anything that you would use in a regular Google search. e.g. inurl:, site:, intitle:. We also support advanced search query parameters such as as_dt and as_eq. |
TDQS
C2.7/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Fetch' implies a read operation, but it doesn't disclose critical traits like rate limits, authentication needs, response format, pagination, or error handling. For a search tool with zero annotation coverage, this is a significant gap.
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 extremely concise with just three words, front-loaded and zero waste. Every word ('Fetch Google Search Results') directly contributes to stating the tool's purpose without unnecessary elaboration.
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 tool's complexity (search functionality with parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain return values, error cases, or behavioral constraints, leaving the agent with insufficient information to use the tool effectively beyond basic input.
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?
Schema description coverage is 100%, so the schema already documents all three parameters (query, gl, hl) with clear descriptions. The description adds no additional meaning beyond what the schema provides, such as examples or usage tips. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Fetch Google Search Results' states the basic action (fetch) and resource (Google Search Results), but it's vague about scope and format. It doesn't specify what kind of results (e.g., web pages, images, news) or how many results are returned. Without sibling tools, differentiation isn't needed, but the purpose could be more specific.
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. There are no sibling tools mentioned, so no explicit comparisons are needed, but it lacks context about use cases, prerequisites, or limitations. It's a generic statement with no usage instructions.
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 tool update
v1.0.0- First observed
google-search
TDQS
C2.9/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'google-search' has a clear and distinct purpose of fetching Google search results, so agents cannot misselect between multiple options.
Naming Consistency5/5
The single tool name 'google-search' follows a consistent pattern of verb-noun (search as the verb, Google as the noun context), and with only one tool, there is no inconsistency to evaluate. The naming is clear and adheres to a predictable structure.
Tool Count2/5
The server has only one tool, which feels thin and under-scoped for a scraping-related domain. A single tool for fetching Google search results may not provide sufficient coverage for typical scraping workflows, such as parsing results, handling pagination, or interacting with other search engines, making it borderline too few for the apparent purpose.
Completeness2/5
Inferring the domain as web scraping or search data fetching, the tool surface is severely incomplete. It only offers a basic search fetch without supporting operations like filtering results, extracting specific data, managing queries, or integrating with other scraping tasks, leading to significant gaps that could cause agent failures in broader scraping scenarios.
Maintenance
ActivityMaintained
ResponsivenessUnresponsive
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
MCP server for Google search results via SERP API
Free web search for AI agents. No API key required. Hosted MCP in active development.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots.3999 npm20MIT
- AlicenseAqualityCmaintenanceA Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots in real-time.4999 npm9MIT
- FlicenseAqualityDmaintenanceA Model Context Protocol server that provides web and image search capabilities through Google's Custom Search API, allowing AI assistants like Claude to access current information from the internet.22-