Skip to main content
Glama
Sign In
Memorable MCP Server

Memorable MCP Server

by leouofa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

memorable_search

Search stored memories using vector similarity or keyword matching, with automatic fallback between modes. Retrieve relevant context by querying persistent memories and limiting results.

Instructions

Unified vector and keyword search across Memorable memories using pgvector cosine similarity or text matching

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": {
      "q": "<q>"
    },
    "name": "memorable_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesSearch query string to find matching memories
modeNoSearch mode: 'auto' (hybrid vector fallback to keyword), 'semantic' (pure pgvector), or 'keyword'
limitNoMaximum number of results to return (1-100, default 20)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does add real behavioral content by revealing the ranking mechanism (cosine similarity vs. text matching) and the auto/hybrid fallback concept, but it omits whether results are score-ordered, what happens when embeddings are absent, and any explicit read-only guarantee.

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?

A single front-loaded sentence with no filler or redundancy; the core purpose and mechanism come first. It is efficient, though its brevity leaves the descriptive burden entirely on the schema.

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

Completeness3/5

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

For a three-parameter read-style search with full schema documentation and no output schema, this is close to adequate but leaves ranking/ordering and result shape unexplained. Nothing an agent needs to form the call is missing, but what to expect back is unstated.

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 coverage is 100%, with all three parameters already documented in detail including the mode enum semantics and the 1-100 limit range. The description only echoes 'vector and keyword', which the schema explains more precisely, so it adds no meaning beyond the structured data.

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 across Memorable memories) and names the retrieval mechanism (pgvector cosine similarity or text matching), which distinguishes it from a pure vector-neighbor tool. It stops short of naming any sibling, so an agent must infer how it differs from memorable_find_neighbors or memorable_recall_context.

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?

The word 'unified' implies this is the general-purpose entry point for retrieval, but the description never says when to prefer it over the semantic-only or context-recall siblings, nor does it state prerequisites such as needing embeddings to exist. Guidance is implied rather than stated.

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