MCP JinaAI Search Server
búsqueda mcp-jinaai
⚠️ Aviso
Este repositorio ya no se mantiene.
La funcionalidad de esta herramienta ahora está disponible en mcp-omnisearch , que combina múltiples herramientas MCP en un paquete unificado.
Utilice mcp-omnisearch en su lugar.
Un servidor de Protocolo de Contexto de Modelo (MCP) para integrar la API de búsqueda de Jina.ai con LLM. Este servidor proporciona funciones de búsqueda web eficientes y completas, optimizadas para recuperar contenido limpio y compatible con LLM de la web.
Related MCP server: Jina AI Remote MCP Server
Características
🔍 Búsqueda web avanzada a través de la API de búsqueda de Jina.ai
🚀 Recuperación de contenido rápida y eficiente
📄 Extracción de texto limpio con estructura preservada
🧠 Contenido optimizado para LLM
🌐 Soporte para varios tipos de contenido, incluida documentación
🏗️ Construido sobre el Protocolo de Contexto Modelo
🔄 Almacenamiento en caché configurable para mejorar el rendimiento
🖼️ Recopilación opcional de imágenes y enlaces
🌍 Soporte de localización a través de la configuración regional del navegador
🎯 Control del presupuesto de tokens para el tamaño de la respuesta
Configuración
Este servidor requiere configuración a través de su cliente MCP. A continuación, se muestran ejemplos para diferentes entornos:
Configuración de Cline
Agregue esto a su configuración de Cline MCP:
{
"mcpServers": {
"jinaai-search": {
"command": "node",
"args": ["-y", "mcp-jinaai-search"],
"env": {
"JINAAI_API_KEY": "your-jinaai-api-key"
}
}
}
}Escritorio Claude con configuración WSL
Para entornos WSL, agregue esto a su configuración de Claude Desktop:
{
"mcpServers": {
"jinaai-search": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"JINAAI_API_KEY=your-jinaai-api-key npx mcp-jinaai-search"
]
}
}
}Variables de entorno
El servidor requiere la siguiente variable de entorno:
JINAAI_API_KEY: Su clave API de Jina.ai (obligatoria)
API
El servidor implementa una única herramienta MCP con parámetros configurables:
buscar
Busca en la web y obtén contenido limpio y compatible con LLM con Jina.ai Reader. Muestra los 5 mejores resultados con URL y contenido limpio.
Parámetros:
query(cadena, obligatoria): Consulta de búsquedaformat(cadena, opcional): Formato de respuesta ("json" o "texto"). El valor predeterminado es "texto".no_cache(booleano, opcional): Omite la caché para resultados actualizados. El valor predeterminado es falso.token_budget(número, opcional): Número máximo de tokens para esta solicitudbrowser_locale(cadena, opcional): configuración regional del navegador para representar el contenidostream(booleano, opcional): Habilita el modo de transmisión para páginas grandes. El valor predeterminado es falso.gather_links(booleano, opcional): Recopila todos los enlaces al final de la respuesta. El valor predeterminado es falso.gather_images(booleano, opcional): Recopila todas las imágenes al final de la respuesta. El valor predeterminado es falso.image_caption(booleano, opcional): Subtitula las imágenes del contenido. El valor predeterminado es falso.enable_iframe(booleano, opcional): Extrae contenido de los iframes. El valor predeterminado es falso.enable_shadow_dom(booleano, opcional): Extrae contenido del shadow DOM. El valor predeterminado es falso.resolve_redirects(booleano, opcional): Sigue las cadenas de redireccionamiento hasta la URL final. Valor predeterminado: verdadero.
Desarrollo
Configuración
Clonar el repositorio
Instalar dependencias:
pnpm installConstruir el proyecto:
pnpm run buildEjecutar en modo de desarrollo:
pnpm run devPublicación
Crear un conjunto de cambios:
pnpm changesetVersionar el paquete:
pnpm versionConstruir y publicar:
pnpm releaseContribuyendo
¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios.
Licencia
Licencia MIT: consulte el archivo LICENCIA para obtener más detalles.
Expresiones de gratitud
Construido sobre el Protocolo de Contexto Modelo
Desarrollado por la API de búsqueda de Jina.ai
Available Tools
1 toolsearchB
Search the web and get clean, LLM-friendly content using Jina.ai Reader. Returns top 5 results with URLs and clean content.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| format | No | Response format (json or text) | text |
| no_cache | No | Bypass cache for fresh results | |
| token_budget | No | Maximum number of tokens for this request | |
| browser_locale | No | Browser locale for rendering content | |
| stream | No | Enable stream mode for large pages | |
| gather_links | No | Gather all links at the end of the response | |
| gather_images | No | Gather all images at the end of the response | |
| image_caption | No | Caption images in the content | |
| enable_iframe | No | Extract content from iframes | |
| enable_shadow_dom | No | Extract content from shadow DOM | |
| resolve_redirects | No | Follow redirect chains to final URL |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool returns 'clean, LLM-friendly content' and 'top 5 results with URLs and clean content,' which gives some behavioral context. However, it lacks critical information about rate limits, authentication requirements, error conditions, or what constitutes 'clean' content, leaving significant gaps for a tool with 12 parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise and front-loaded: a single sentence that communicates the core functionality, method, and output format. Every word earns its place with zero redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 12 parameters and no output schema, the description provides basic purpose and output format but lacks sufficient behavioral context. Without annotations covering safety, limits, or authentication, and with no output schema to explain return values, the description should do more to compensate for these gaps, especially given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 12 parameters. The description doesn't add any parameter-specific information beyond what's already in the schema descriptions. According to guidelines, when schema coverage is high (>80%), the baseline score is 3 even with no parameter information in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search the web and get clean, LLM-friendly content using Jina.ai Reader.' It specifies the action (search), resource (web content), and processing method (Jina.ai Reader). However, without sibling tools, it cannot demonstrate differentiation from alternatives, preventing a score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 contextual constraints. It mentions returning 'top 5 results' but doesn't explain when this limitation is appropriate or when other search tools might be better suited.
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
search
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'search' has a clear and singular purpose, making it impossible for an agent to misselect among non-existent alternatives.
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The name 'search' follows a simple verb pattern, which is appropriate and unambiguous for its function.
A single tool is too few for a server named 'MCP JinaAI Search Server', which suggests a broader search functionality scope. While the tool covers basic web search, the server lacks additional tools for advanced operations like filtering, pagination, or domain-specific searches, making it feel thin and under-scoped.
The server is severely incomplete for a search domain. It only offers a basic search tool without any supporting operations such as refining queries, handling multiple result pages, or accessing search history. This creates significant gaps that could lead to agent failures when more complex search tasks are required.
Maintenance
Related MCP Connectors
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
The best web search for your AI Agent
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables web content retrieval and semantic search capabilities through the Jina AI API. Provides tools to fetch content from URLs and perform intelligent web searches with natural language queries.3MIT
- AlicenseNot gradedqualityCmaintenanceProvides access to Jina AI's web reading, search, embeddings, and reranking capabilities. Enables URL content extraction, web/arXiv/image search, document deduplication, and relevance ranking through natural language.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides web content extraction, search capabilities (web, arXiv, SSRN, images), semantic deduplication, and reranking through Jina AI's Reader, Embeddings, and Reranker APIs.1Apache 2.0
- AlicenseBqualityAmaintenanceIntegrates Jina AI Search Foundation APIs to provide web page content extraction and search capabilities. It supports automatic pagination, result caching, and both standard and VIP search endpoints for enhanced information retrieval.1127 npm45MIT