Skip to main content
Glama
Sign In
mcp-memoria

mcp-memoria

by lucabaello1998
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

buscar_memoria

Search indexed notes, agent memories, and READMEs for documented goals, projects, decisions, or contacts; returns file:line-cited snippets so agents verify context before asking the user.

Instructions

Busca en la memoria del usuario (notas, memorias de agentes y READMEs indexados) y devuelve fragmentos con cita exacta archivo:línea. Usala antes de preguntar algo que el usuario ya documentó: objetivos, proyectos, decisiones, datos de contacto, cómo trabaja. Una lista vacía significa que no hay nada indexado sobre el tema.

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": {
      "consulta": "<consulta>"
    },
    "name": "buscar_memoria"
  }
}

Input Schema

NameRequiredDescriptionDefault
modoNoauto (por defecto) usa híbrido si el índice tiene embeddings y léxico si no. bm25 fuerza búsqueda por palabras; hibrido suma similitud semántica.
limiteNoCuántos fragmentos devolver (1 a 20, por defecto 5).
consultaYesTexto libre, por ejemplo "objetivos búsqueda laboral" o "decisiones de FletAR".
etiquetaNoFiltra por etiqueta de fuente, por ejemplo "memoria", "notas" o "repos".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does disclose useful behavior: results come back as fragments with exact `archivo:línea` citations, and an empty list is defined as 'nothing indexed on the topic'. It does not mention index freshness or that reindexar may be needed when results are stale, which is the main remaining behavioral gap for a search tool.

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?

Three sentences, front-loaded with the core action and return format, then the usage trigger, then the empty-result semantics. Every sentence carries distinct information with no repetition of the schema.

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 4-parameter read tool with no output schema, the description covers what is searched, what is returned (fragments with citations), and how to interpret an empty result. It leaves out relevance ordering and index-staleness guidance, which would round out completeness but are not blocking.

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 enum modes, the 1-20 limit, and the etiqueta filter are already fully documented in the schema. The description adds no extra meaning about parameters beyond that baseline, which is acceptable but not additive.

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?

States a specific verb (busca) and resource (memoria del usuario) and enumerates the indexed sources (notas, memorias de agentes, READMEs), which implicitly separates it from siblings like listar_fuentes or leer_fragmento. It also names the return shape (fragmentos con cita `archivo:línea`), but never explicitly contrasts itself with an alternative tool, so it stops short of the top band.

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

Usage Guidelines4/5

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

Gives a clear trigger condition: use it before asking the user something they already documented, with concrete examples (objetivos, proyectos, decisiones, datos de contacto, cómo trabaja). It does not state when NOT to use it or point to a specific alternative such as leer_fragmento or listar_fuentes, so it lacks the explicit routing of a 5.

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

Deploy Server

Other Tools