Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
memory_schemaA

Return CP Memory schema explanations and whether FTS is available.

memory_addC

Add or update a memory fact. Supports explicit category and optional long-form content payload.

memory_personal_addC

Add or update a long-term personal assistant memory using Profile, Preference, Relationship, Ongoing, Episode, or BeliefDecision.

memory_personal_deriveB

Derive a long-term personal memory from an existing Episode and link it back to the source episode.

memory_episode_consolidateC

Preview or apply conservative Episode consolidation into long-term personal memories.

memory_personal_listC

List personal assistant memories, optionally filtered by the six-model memory type.

memory_personal_reviewC

Return a user-facing personal memory review dashboard with counts, recent memories, conflicts, and consolidation candidates.

memory_review_digestA

Return a Markdown memory review digest with recent memories, pending auto-extracts, conflicts, stale candidates, and resolution suggestions.

memory_review_inboxB

Show a small actionable inbox for pending memory review. This previews items only and never deletes memory.

memory_review_applyA

Apply one explicit memory review action: confirm, wrong, stale, scoped, or skip. This never physically deletes memory.

memory_correctB

Mark a memory as corrected, stale, wrong, scoped, or confirmed; optionally replace its value.

memory_personal_resolveB

Resolve a personal-memory conflict by confirming or merging one winner and marking other memories stale, wrong, or scoped with audit links.

memory_searchC

Search memories using FTS when available, with OR ranking by default or strict AND matching.

memory_probeA

Get all facts about an entity. Aliases resolve to the canonical entity first.

memory_explainB

Explain a memory record, including meta, payload, and relations.

memory_inspectC

Inspect a memory record in a user-friendly way, including where the preview, payload, and relations live.

memory_alias_addC

Add or update an alias for a canonical entity.

memory_alias_listA

List aliases, optionally filtered by canonical entity.

memory_updateC

Update an existing fact value, confidence, category, or content payload.

memory_removeA

Delete a fact by ID, including its metadata, payload, and graph links.

memory_listB

List recent facts, optionally filtered by category.

memory_statsB

Get memory statistics across facts, payloads, decisions, workflows, aliases, and relations.

memory_healthB

Return CP Memory health, migration state, FTS state, and active task.

memory_decision_addB

Record an architecture or technical decision and mirror it into facts with strong metadata.

memory_decision_listA

List recorded decisions, most recent first.

memory_task_setC

Set the current active task.

memory_task_getA

Get the current active task.

memory_task_doneC

Mark the current task as complete with a result summary.

memory_workflow_saveC

Save a reusable workflow or procedure.

memory_workflow_getA

Get a saved workflow by name.

memory_workflow_listB

List saved workflows.

memory_link_addC

Create an explicit memory relation between two records.

memory_link_listC

List explicit memory relations.

memory_touchC

Mark matching memories as accessed, optionally by IDs.

memory_conflictsB

Find possible conflicting memories, including duplicate facts and personal-memory contradictions.

memory_maintenanceC

Run memory maintenance: backfill meta, rebuild indexes, and optionally expire low-value records.

memory_governance_reportB

Build a non-destructive governance acceptance report over the current memory.db, including auto-extract review queue, conflict samples, corrected samples, and restore probes.

memory_auto_extract_cleanupA

Preview or apply cleanup for auto-extracted noise records that look like implementation explanations rather than real user memory. Prefer action=mark_wrong for safer governance; use delete only when you really want to remove rows.

memory_restore_contextB

Build a compact restored context for startup, history recovery, or project continuation.

memory_recallB

CP Memory-first recall入口。任何记忆相关问题都先查 CP Memory 主库,再根据主库命中质量决定是否补查 Codex 自带 memory 作为辅助背景。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.9/5.0

Scored across 40 tools

Disambiguation2/5

Several tools have unclear boundaries: memory_add vs memory_update vs memory_personal_add overlap, and memory_correct, memory_review_apply, and memory_personal_resolve all support similar marking actions. The review cluster (memory_personal_review, memory_review_digest, memory_review_inbox) and retrieval cluster (memory_search, memory_recall, memory_restore_context) also create confusion.

Naming Consistency3/5

Most tools follow a memory_<noun>_<verb> pattern, but there are notable exceptions like memory_add, memory_list, memory_recall, memory_restore_context, memory_review_digest, and memory_review_inbox. The naming is readable and consistently prefixed with memory_, but the mixed verb/noun order and noun-only names prevent a higher score.

Tool Count2/5

At 40 tools, this server is overbuilt for a coherent tool set. Many tools could be consolidated, especially the review, correction, and inspection clusters, which inflate the count without adding clear distinct value.

Completeness4/5

The core memory lifecycle is well covered with add, update, remove, search, inspect, aliases, links, conflicts, maintenance, and governance tools. Minor gaps exist in subdomains such as workflows, decisions, aliases, and links, where add/list/save exists but dedicated remove/update operations are missing or indirect.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive