Skip to main content
Glama
persistent-memory-mcp

persistent-memory-mcp

Derive from exact parents

memory_derive

Stores summaries, conclusions, or procedures built from existing memory entries, linked to the exact source versions so corrections or withdrawals invalidate the artifact and notify sessions that saw it.

Instructions

Store a summary, conclusion or procedure you built from entries already in memory, linked to the exact versions it came from. Use it instead of memory_remember whenever the text depends on stored entries: if one of them is later corrected or withdrawn, this artifact stops being served and sessions that saw it are notified. Returns artifact_id and ref.

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": {
      "text": "<text>",
      "parents": "<parents>"
    },
    "name": "memory_derive"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoobservation for a fact, document for a text, procedure for how to do something, task, feedback, or hypothesis for a guess nobody confirmed.
textYesThe derived statement, self-contained.
aliasesNoShort names to find it again.
parentsYesThe refs it was built from, as returned by memory_search.
confidenceNoDeclared, not computed. Leave out unless the user gave one.
valid_fromNoUTC time it starts to apply, e.g. 2026-01-31T00:00:00Z. Leave out unless the user gave one; by default it applies now.
artifact_idNoStable name you choose. Leave out to get one.
valid_untilNoUTC time after which it no longer applies. Leave out unless the user gave one.
preconditionsNoExact conditions a search must supply to see it. Leave out unless the user said it only holds under a condition: a search without these conditions will not return it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world write, so the description's job is incremental. It does that well by disclosing dependency-invalidation behavior (artifact stops being served and prior viewers are notified when a parent is corrected or withdrawn) and stating the return values artifact_id and ref. It leaves out whether repeated calls without an explicit artifact_id create duplicates, which is exactly the nuance the non-idempotent hint raises.

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 what is stored and how it is linked, followed by the selection rule and the failure behavior. No filler and nothing buried.

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?

For a 9-parameter write tool with nested ref objects and no output schema, the description supplies the missing pieces an agent needs: when to prefer it, what happens on parent invalidation, and what the call returns. Remaining parameter detail is fully carried by the schema.

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% and the schema already defines kind, text, parents, relation, confidence, validity windows, preconditions and artifact_id in detail. The description reinforces the parents linkage and the artifact_id/ref return, but adds no syntax or edge-case meaning beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource: storing a summary/conclusion/procedure built from entries already in memory, linked to the exact versions it came from. It explicitly distinguishes itself from memory_remember for the case where the text depends on stored entries, so an agent can separate the two without opening schemas.

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?

Gives an explicit routing rule: 'Use it instead of memory_remember whenever the text depends on stored entries,' plus the consequence that motivates the choice. The condition that selects this tool versus its closest sibling is named directly rather than implied.

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