curator-mcp

Store Memory

store_memory

Save personal preferences, habits, goals, or hard directives into long-term memory so the AI curator recalls and applies them in future conversations.

Instructions

Store a personal preference, habit, directive, or constraint in long-term memory.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No	Optional topic keywords for indexing (e.g. ['coffee', 'beverages']).
`content`	Yes	The fact, preference, or directive to remember (e.g. 'Prefers dark roast pour-overs').
`category`	No	'preference', 'dislike', 'goal', 'habit', 'context', or 'directive'.	preference
`importance`	No	Integer priority from 1 (minor quirk) to 5 (critical hard directive).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Sep 11, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It does not explain persistence semantics, whether duplicate memories are merged, what happens on retrieval, or any permissions or side effects. Only the base action is stated, leaving significant gaps for a mutation-style tool.

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 description is a single, front-loaded sentence with no filler. It is efficient, though its extreme brevity pushes against the informational needs of the tool rather than being a structural flaw.

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

Completeness2/5

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

Given a four-parameter mutation tool with no annotations and an output schema that handles return values, the description is too thin. It omits routing guidance relative to recall_memories, behavioral details about long-term storage, and any indication of scope or deduplication, leaving an agent under-informed for correct invocation.

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 schema already documents all four parameters in detail. The description adds a loose content-type list that partially overlaps with the category values, but provides no additional syntax, constraints, or examples beyond what the schema already gives. A baseline 3 is appropriate.

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?

The description states a specific verb ('Store') and resource ('long-term memory'), and enumerates the kinds of content accepted (preference, habit, directive, constraint). This clearly distinguishes it from the retrieval-oriented sibling recall_memories, though it does not name that sibling explicitly.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives such as recall_memories or the many domain-specific logging/search tools. The description merely states what it does; an agent must infer the appropriate context from the tool name alone.

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