Skip to main content
Glama
AleBrito124356

mcp-memory-vault

by AleBrito124356
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Search memories

recall
Read-only

Search stored memories by full text and get top matches ranked by relevance, with partial matches returned when no exact term matches.

Instructions

Search memories by full text and get the best matches first.

Punctuation and filler words ("when", "does", "the", "de", "que"...) are ignored and words also match by prefix, so plain questions work. With the default match="auto", memories containing every term come first; if none do, partial matches are returned instead, ranked by how many terms they contain, and the result carries a "note" saying so. Ranking uses SQLite FTS5 bm25 relevance with recency as tiebreaker.

Returns {"query", "terms", "search_mode", "match_mode", "count", "hits"} where each hit has id, content, snippet (matches in [brackets]), matched_terms, namespace, tags, source, created_at, updated_at and age. A "hint" explains what to try when nothing matched.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoOnly return memories carrying ALL of these tags (case-insensitive).
limitNoMaximum number of hits.
matchNo"all" = every term must match; "any" = at least one, most terms first; "auto" = "all", falling back to "any" when nothing matches every term.auto
queryYesWhat to look for: key nouns ("ACME deploy") or a plain question ("when does ACME deploy?").
namespaceNoOnly search this namespace ("" = all namespaces).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and openWorldHint, yet the description goes well beyond them: it discloses the ranking algorithm (SQLite FTS5 bm25 with recency tiebreaker), the auto-match fallback behavior, the 'note' emitted on partial matches, and the 'hint' on empty results. That is genuine behavioral context an agent would otherwise have to discover by trial.

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?

The search behavior is front-loaded and the return-shape paragraph is dense but skimmable. The sentence enumerating every hit field is somewhat list-like, but no sentence is redundant given the absence of an output schema.

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?

With no output schema, the description carries the return contract and does so fully: the top-level envelope keys, per-hit fields, snippet bracketing, the note flag and the hint. Combined with annotations, an agent has everything needed to invoke and interpret recall.

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

Parameters4/5

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 real meaning on top: it clarifies that plain questions work, that terms match by prefix, and that match='auto' falls back from all to any with an accompanying note. These reinforce and extend the enum and query descriptions.

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 and resource ('Search memories by full text') plus a scope promise ('best matches first'). It contrasts implicitly with list_memories by emphasizing relevance ranking and full-text matching, but never names a sibling to sharpen the boundary.

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?

Explains what happens with punctuatation, filler words and prefix matching, and describes the default match='auto' fallback chain, which tells the agent how the search behaves. However, it never states when to reach for recall versus list_memories or memory_stats, so the usage context is only implied.

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