LABSCO SUMMARY
Versioned memory with a preview before you restore it.
Most memory servers let you overwrite and hope; here every change is recorded, restore can run in preview mode first, and a backup is taken before the rollback lands. The importance score is the other useful piece — searching with a minimum importance is a far better filter than recency when the store gets large.
What it is
A local work-memory store. Memories carry a project, tags, an importance score and a creator; search filters on all of them, and every change is versioned so an edit can be undone.
What you get
- add_work_memory — store content with a project, tags, an importance score and a creator
- search_work_memory — search with filters for project, tags, importance range, creator and date range, sorted by time, importance or relevance
- list_work_memories — browse with filters and a choice of summary, detailed or minimal output
- delete_work_memory — delete or archive a memory, with an explicit confirmation flag
- get_related_keywords — keywords related to one you give, with a similarity threshold
- get_search_stats — memory counts, popular tags, project distribution and index state
- optimize_search_index — rebuild the index and clear orphaned entries
- get_work_memory_history — change history filtered by memory, type (create, update, delete, archive), date, project or creator
- get_work_memory_versions and list_memory_versions — the versions of a memory
- restore_memory_version — roll back fully, selectively by field, or as a preview, with a backup taken first
- get_server_status — server health, statistics and component checks
Requirements
Node.js 18 or higher. Clone the repository and build it — the npm package and release binaries its install guide mentions have not been published. Point the client at the built entry file and set WORK_MEMORY_DIR to the directory the data should live in; LOG_LEVEL, MAX_MEMORY_SIZE and the cache TTL are optional.
Setup effort
Build from source — git clone https://github.com/moontmsai/work-memory-mcp.git
USE CASES
01
Ending a work session cleanly
Write down what you did with the project, tags and an importance score attached.
02
Picking up where you left off
Search the project's memories above an importance threshold, most relevant first.
03
Finding related work you forgot about
Ask for keywords related to the one you are looking at and follow them.
04
Undoing a bad edit
Read the memory's history and versions, preview the restore, then apply it with a backup.
05
Keeping search fast as the store grows
Read the search statistics and rebuild the index when it has drifted.
06
Archiving instead of deleting
Archive the memory so it leaves the active set but stays recoverable.
BEFORE YOU INSTALL
What to know first
Requires
- node on PATH
- Node.js 18.0.0 or later
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/moontmsai/work-memory-mcp.git
cd work-memory-mcp
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"work-memory": {
"command": "node",
"args": [
"/PATH/work-memory-mcp/dist/index.js"
],
"env": {
"WORK_MEMORY_DIR": "/PATH/work-memory-mcp/data/",
"LOG_LEVEL": "WARN",
"NODE_ENV": "production"
}
}
}
}/PATH is the folder that holds your work-memory-mcp clone. Config file: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) · %APPDATA%\Claude\claude_desktop_config.json (Windows) · ~/.config/claude-desktop/claude_desktop_config.json (Linux)
Cursor
CURSOR · JSON
{
"mcpServers": {
"work-memory": {
"command": "node",
"args": [
"<YOUR_PATH_TO_WORK_MEMORY_MCP>/dist/index.js"
],
"cwd": "<YOUR_PATH_TO_WORK_MEMORY_MCP>",
"env": {
"WORK_MEMORY_DIR": "<YOUR_WORK_MEMORY_DIR>",
"LOG_LEVEL": "INFO"
}
}
}
}~/.cursor/mcp.json (all projects) · .cursor/mcp.json (one project)