memory-ultra-rag-mcp

Overview Schema Source Related Servers Discussions Admin

recall_memory

Read-onlyIdempotent

Searches joined project and account memories by matched words or meaning, returns ranked statements naming their scope, and supports filtering by kind plus limiting results.

Instructions

Returns what is remembered that matches these words.

It searches this project's memory and the account's memory together and ranks the results by how well they match, so the best statement wins whichever memory it is in. Each one names its scope.

Give it a few words, not a sentence. When nothing comes back, that is what the search found: try other words, or pass a kind.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Return only the statements filed under this kind, one word in block letters. A kind is a column of the record rather than part of a statement's words, so it is asked for here rather than searched for.
`limit`	No	How many statements to return across both memories, at most 50. This caps matches, not the size of a file read.
`query`	Yes	What to recall, as words. Answered from the statements that match, by their words and by their meaning. Required: this server answers a question rather than returning a memory whole.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.8.0Sep 30, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/closed-world, but the description adds real behavior beyond them: results span two memory scopes, are ranked by match quality, each names its scope, and an empty return means 'not found' rather than an error. That empty-result semantics is valuable and not derivable from annotations.

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?

Short and front-loaded with the core action, then layered constraints. The prose style is somewhat ornate ('so the best statement wins whichever memory it is in'), but no sentence is truly wasted.

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?

With an output schema present and annotations covering safety, the description needs only to convey scope and empty-result behavior, which it does. Minor gaps: no explicit sibling routing or pagination note, but nothing essential is missing.

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%, so each parameter is already documented. The description adds only marginal meaning — implying query is a few words and that 'kind' can be passed to widen a failed search — so the baseline 3 applies.

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 — returns remembered statements matching given words — and clarifies it searches project and account memory together with ranking. The distinction from siblings (record_/forget_) is inferable from the verb but not called out explicitly.

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 concrete usage advice: 'Give it a few words, not a sentence' and, on empty results, 'try other words, or pass a kind.' This tells the agent how to use and recover, though it never explicitly names alternative tools.

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

Deploy Server