Skip to main content
Glama
Sign In
Unified Memory MCP

Unified Memory MCP

by piligrim-code
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_recall

Retrieve the most relevant memory chunks by meaning for a query, with keyword fallback when embeddings are disabled.

Instructions

Semantic recall from memory: returns the most RELEVANT chunks by meaning (cosine over embeddings), falling back to keyword search if embeddings are off. Prefer this over memory_search when you want the best context for a topic.

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": "memory_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoHow many chunks (default 5).
queryYesWhat you want to recall.
scopeNoOptional scope filter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.5.1

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the behavioral burden. It discloses the ranking method (cosine over embeddings) and the server-side fallback to keyword search when embeddings are off, which is important non-obvious behavior. It does not discuss permissions, side effects, or return format, but for a recall tool the disclosed ranking and fallback behavior are the central traits.

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?

Two sentences, front-loaded with the tool's primary behavior and then the sibling routing condition. Every clause earns its place; there is no filler.

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?

The tool has three fully documented parameters, no output schema, and no annotations. The description states that it returns chunks, how relevance is computed, and what happens when embeddings are off, which covers the main calling context. It could say more about the returned chunk representation, but is adequate for a recall operation.

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 input schema already documents query, k, and scope. The description adds no parameter-level detail beyond the schema, which makes the baseline of 3 appropriate.

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?

The description states a specific verb and resource: semantic recall from memory that returns relevant chunks by meaning. It explicitly contrasts itself with the sibling memory_search, so an agent can select between them 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?

It gives an explicit use condition: 'Prefer this over memory_search when you want the best context for a topic.' This names the alternative and the circumstance that selects this tool, leaving little to inference.

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