add_observations
Add new observations to existing entities in the knowledge graph
LABSCO SUMMARY
Per-project memory files are the fix for one giant shared graph.
The upstream Memory server keeps everything in one place; here the file path travels with the call, so work notes and personal notes stay apart. Getting the benefit means the model has to pass that path every time — which is why the README ships a system prompt rather than leaving it to chance.
What it is
A knowledge-graph memory server built on the MCP team's Memory server, with two things added: the memory file path can be set per call, so each project keeps its own graph, and the server can produce timestamps to attach to what it stores.
What you get
- Entities, relations and observations created, read and deleted across a persistent knowledge graph
- The whole graph read back, searched by term, or opened at specific nodes
- A memory file path chosen per project rather than one shared store — pass it with each operation
- A current timestamp on demand, so entities and observations can record when they were written —
get_current_time - A system prompt in the README that tells the model when to retrieve, what to record (identity, behaviours, preferences, goals, relationships) and when to update
Requirements
Node.js version 16 or higher. No account and no key. Run the built dist/index.js as a Node process. MEMORY_FILE_PATH sets the default store; without it the server writes memory.json next to the script. Installable into Claude Desktop through Smithery. The package is memory-custom 1.0.0.
Setup effort
One command — npx -y github:BRO3886/mcp-memory-custom
USE CASES
01
Keeping what the assistant remembers about two projects separate
Give each project its own memory file path and pass it on every memory operation, so a fact learned in one never surfaces in the other.
02
Building up a picture of a person or team over many sessions
Create entities for the recurring people, organisations and events, connect them with relations, and store facts as observations. Attach a timestamp so you can tell later what was learned when.
03
Starting a session with what you already know
Search the graph for terms relevant to the task and open the matching nodes, so the conversation begins from stored context instead of re-asking.
10 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
create_entities
Create multiple new entities in the knowledge graph
create_relations
Create multiple new relations between entities in the knowledge graph. Relations should be in active voice
delete_entities
Delete multiple entities and their associated relations from the knowledge graph
delete_observations
Delete specific observations from entities in the knowledge graph
delete_relations
Delete multiple relations from the knowledge graph
get_current_time
Get the current time
open_nodes
Open specific nodes in the knowledge graph by their names
read_graph
Read the entire knowledge graph
search_nodes
Search for nodes in the knowledge graph based on a query
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools when we connected.
Requires
- npx on PATH
- Node.js
CONTEXT COST
Light Standing cost
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mcp-memory-custom": {
"command": "npx",
"args": [
"-y",
"github:BRO3886/mcp-memory-custom"
]
}
}
}npx
TERMINAL
npx -y github:BRO3886/mcp-memory-custom
