Skip to main content
Glama
piligrim-code

Unified Memory MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CLAUDE_MEM_DIRNoDirectory of reviewed local assistant memory to import when MEMORY_AUTOSYNC=1.
CLAUDE_MEM_GLOBNoGlob pattern selecting reviewed local assistant memory files to import when MEMORY_AUTOSYNC=1.
MEMORY_AUTOSYNCNoSet to 1 to enable explicit import of local assistant memory; default is no automatic import.0
UNIFIED_MEMORY_DBYesAbsolute path to the SQLite database file, e.g. /absolute/private/path/memory.db.
MEMORY_GATEWAY_TOKENNoAuthentication token for the optional HTTP gateway. Use either MEMORY_GATEWAY_TOKEN or MEMORY_GATEWAY_TOKEN_FILE.
MEMORY_GATEWAY_TOKEN_FILENoPath to a file containing the HTTP gateway authentication token. Use either MEMORY_GATEWAY_TOKEN or MEMORY_GATEWAY_TOKEN_FILE.

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
}

Tools

Functions exposed to the LLM to take actions

NameDescription
memory_saveA

Save a memory (fact, preference, decision, context) to the shared local store that both Codex and Claude read. Auto-chunked and embedded for semantic recall. Use for durable info worth recalling.

memory_recallA

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.

memory_searchC

Full-text (keyword) search of whole memories. Returns ranked matches.

memory_reindexA

Rebuild chunks + embeddings for all memories. Run once after enabling embeddings (fastembed).

memory_policyB

Report content-free scope authorization, quota, retention, and usage state.

memory_pruneC

Delete expired memories and completed handoffs. Requires confirm=true.

memory_syncA

Pull Claude's file memories (*.md) into the store. Idempotent and cheap: only files whose content changed are rewritten and re-embedded. Runs automatically on server start.

memory_bootstrapA

Start or resume work across Codex and Claude. Returns the latest active handoff from another client plus relevant durable memory chunks. Call once at the beginning of substantial work.

handoff_saveC

Create or update a structured work checkpoint so another Claude/Codex session can continue from the same state. Reuses project+source+session_id.

handoff_loadC

Load recent unfinished handoffs for a project, normally from another client.

handoff_listC

Audit recent handoff checkpoints for a project.

handoff_completeC

Mark a handoff complete once the transferred task is finished.

memory_listC

List most recently updated memories, optionally filtered by scope or tag.

memory_getC

Fetch a single memory by id.

memory_updateB

Update a memory's content, tags, or scope by id (re-chunks on content change).

memory_deleteC

Delete a memory by id.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.2/5.0

Scored across 16 tools

Disambiguation4/5

Most tools have clearly distinct purposes, but memory_search and memory_recall overlap as search mechanisms, and memory_bootstrap overlaps with handoff_load/handoff_list by also returning handoff data. Descriptions help clarify preferred usage, so misselection is unlikely for careful agents.

Naming Consistency5/5

All tool names use consistent snake_case with a predictable domain prefix: memory_ or handoff_. Actions are generally verbs and the pattern is stable across the set.

Tool Count4/5

16 tools is slightly above the typical 3-15 range, but each tool serves a distinct role in memory management or handoff lifecycle. The set is rich but not bloated.

Completeness4/5

The surface covers memory CRUD, search, recall, admin tasks, and handoff lifecycle, so core workflows are complete. Minor gaps include no direct handoff_get by id, though handoff_load/list and memory_prune cover most needs.

Maintenance

ActivityMaintained
ResponsivenessNo issues