Skip to main content
Glama
multimedia-search-mcp

multimedia-search-mcp

search_media

Search movies, series, anime, books, manga, and other media across configured providers, filtering by title, year, type, and categories to return normalized results.

Instructions

Busca contenido multimedia en los proveedores configurados.

Args: query: Título o términos de búsqueda. media_type: movie, series, anime, book, manga u other. year: Año de estreno/publicación (solo si el proveedor lo soporta). categories: Filtro explícito de categorías del proveedor: ids numéricos Newznab o nombres exactos del árbol (p. ej. "2040" o "Movies/HD"). Los ids se validan contra el árbol antes de buscar; las categorías nativas de un indexador (p. ej. 130420) se rechazan porque el filtro de Prowlarr es global. Si el árbol no está disponible, los ids se envían sin validar y se avisa. limit: Resultados por página (1-100, por defecto 20). offset: Desplazamiento dentro de la ventana recibida (por defecto 0). provider: Proveedor a usar (por defecto, el primero configurado).

Semántica de la respuesta (deliberadamente conservadora): received_count: resultados recibidos del proveedor (una ventana, no el total del índice). returned_count: resultados de esta página tras limit/offset local. has_more: true si quedan resultados en la ventana recibida; null si no puede determinarse. Nunca false: no se puede demostrar que no haya más. next_offset indica la página siguiente cuando aplica. total_available: null cuando el proveedor no garantiza el total. truncated: true solo si el proveedor aporta evidencia de corte; null si no se sabe (caso de Prowlarr: no hay evidencia). per_indexer: resultados y fiabilidad de la ventana por indexador. category_match: por resultado, in_subtree / off_category / uncategorized (solo con filtro de categorías); resumen en category_match_summary. Los resultados sin categoría se conservan pero no se presentan como coincidencia confirmada.

Una lista vacía no garantiza que no existan coincidencias.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNo
limitNo
queryYes
offsetNo
providerNo
categoriesNo
media_typeNoother

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does so well: it discloses category-id validation against the provider tree, rejection of native indexer ids, fallback to unvalidated ids with a warning, and default provider selection. The deliberately conservative response semantics (has_more never false, total_available/truncated null when unknown, per_indexer reliability, category_match states) are non-obvious behavior that an output schema alone could not convey.

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

Conciseness3/5

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

Purpose is front-loaded and the Args/response split is logical, but the text is long and partly redundant — limit ranges, offset and provider defaults restate the JSON schema, and the response block is extensive for a tool that already ships an output schema. The null-vs-false semantics earn their place; the default restatements do not.

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

Completeness4/5

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

For a 7-parameter search tool with zero schema description coverage and no annotations, this definition covers the essentials: parameter meaning, category validation behavior, and result-window interpretation. It leaves only minor gaps, such as how a caller should discover valid provider names beyond relying on the default.

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 description coverage is 0%, yet every one of the seven parameters is explained with meaning beyond its name: media_type enumerates accepted values, year is flagged as provider-dependent, categories details the id-vs-tree-name format and validation rules, and limit/offset/provider state ranges and defaults. This fully compensates for the empty schema documentation.

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 opening sentence gives a specific verb+resource+scope: searching multimedia content across the configured providers. That is clearly distinct from the sibling read/list tools (list_providers, get_provider_status, list_indexers), though the description never names them to reinforce the split.

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

Usage Guidelines3/5

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

Usage is implied rather than stated — the Args and response sections tell you how to call it once you have decided to, and the closing caveat ('an empty list does not guarantee no matches') shapes interpretation. There is no explicit when-to-use/when-not guidance and no routing toward get_search_capabilities or list_providers for discovery.

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