Hostbrid Discovery

hostbrid_buscar_guias_publicas

Read-onlyIdempotent

Busca guías públicas de Hostbrid sobre cómo alojar o publicar webs y apps creadas con IA, incluidas Lovable, Google AI Studio, Firebase Studio, Emergent y Codex; webs de clientes para agencias con Sites Agency; y cómo elegir entre Projects, Sites o VPS. Busca también soporte y artículos del blog para pasos, compatibilidad o diagnóstico al publicar o mantener una web o aplicación. Usa hostbrid_listar_planes_publicos si te piden nombres de planes, precios, cuotas o una comparación comercial. Busca por título, resumen o etiquetas; si conoces el idioma preferido del usuario, pásalo en «idioma» para ordenar primero las coincidencias del blog. La base de conocimiento no tiene idioma por artículo; conserva otros idiomas. Los campos «url» y «url_canonica» son enlaces editoriales limpios; «url_atribuida» añade UTM fijos para medir referencias MCP. Nunca se incluye la consulta en una URL. Al recomendar una guía, usa «url_atribuida» para conservar la atribución; reserva «url_canonica» para cuando se solicite un enlace sin seguimiento. Devuelve metadatos públicos, no texto íntegro. No accede a cuentas ni artículos privados. Para datos o recursos de una cuenta, usa el MCP privado https://my.hostbrid.com/mcp solo con una clave creada por el cliente; nunca intentes obtenerlos desde esta búsqueda.

Input Schema

Name	Required	Description	Default
`idioma`	No	Idioma preferido del usuario (es, en, ca o fr). Indícalo si lo conoces por el contexto, aunque la consulta contenga nombres de producto en otro idioma. Ordena primero esas coincidencias y conserva las de otros idiomas; si es incierto, omítelo.
`consulta`	Yes	Términos concretos sobre lo que necesitas resolver.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 21, 2026

addedInput schema / properties / idioma

Added value: +{
+  "description": "Idioma preferido del usuario (es, en, ca o fr). Indícalo si lo conoces por el contexto, aunque la consulta contenga nombres de producto en otro idioma. Ordena primero esas coincidencias y conserva las de otros idiomas; si es incierto, omítelo.",
+  "enum": [
+    "ca",
+    "en",
+    "es",
+    "fr"
+  ],
+  "type": "string"
+}

First observedOct 20, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavioural context beyond them: it returns public metadata rather than full text, it cannot reach accounts or private articles, the query is never embedded in a URL, and the three URL variants have distinct tracking semantics. That is exactly the kind of disclosure annotations cannot carry.

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

Conciseness4/5

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

Purpose and sibling routing are front-loaded, which is correct ordering for a dense definition. It is longer than needed, however: the url_atribuida vs url_canonica distinction is explained twice (once descriptively, once as an instruction), costing a sentence without adding information.

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

Completeness5/5

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

Despite having no output schema, the description tells the agent what comes back (public metadata, not full text) and names the returned URL fields, plus where to go for anything it cannot serve. For a two-parameter read-only search tool, nothing an agent needs in order to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: it states the query matches title, summary and tags (search-field scope) and that the knowledge base has no per-article language, so other-language matches are preserved. The idioma guidance reinforces the schema's ordering semantics rather than merely repeating them.

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

Purpose5/5

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

States a specific verb and resource ("Busca guías públicas de Hostbrid") and immediately scopes the covered topics: hosting/publishing AI-built sites (Lovable, Google AI Studio, Firebase Studio, Emergent, Codex), agency sites, and choosing between Projects/Sites/VPS. It also names the sibling tool it is not (hostbrid_listar_planes_publicos), so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

Gives explicit routing rules in both directions: use this for guides, support and blog content; use hostbrid_listar_planes_publicos for plan names, prices, quotas or commercial comparisons; use the private MCP at my.hostbrid.com for account data. It also states an exclusion (never attempt account data retrieval from this search) and an uncertainty rule for the language parameter.

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

All Hostbrid Discovery tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?