add_observations
Add new observations to existing entities in the knowledge graph
LABSCO SUMMARY
Memory with a shape — entities, relations and observations — rather than a growing pile of notes.
Because facts are attached to named entities and joined by typed relations, a later question can be answered by walking the graph instead of re-reading everything. The deletes are the part people underestimate: an observation can be retracted on its own, so a fact that stops being true does not have to live forever next to the ones that still are.
What it is
Persistent memory stored as a local knowledge graph. Entities carry a name, a type and a list of observations; relations connect them in active voice.
What you get
- Entities created in batches, each with a type and its own observations
- Relations between entities, stored directionally and in active voice — works_at, for instance
- Observations added to an entity that already exists, one fact per observation
- Deletion at every level: whole entities and their relations, single relations, or individual observations
- Search across entity names, types and observation text, returning the matches with their relations
- Named nodes opened directly, with the relations that run between them
- The whole graph read back at once, also exposed as a readable resource at memory://knowledge-graph that updates as tools change it
Requirements
No account and no key — storage is a JSONL file on your own disk. Published on npm as @modelcontextprotocol/server-memory and run through npx, or from the mcp/memory Docker image with a volume mounted. MEMORY_FILE_PATH points it at a file of your choosing; without it, memory.jsonl in the server directory is used.
Setup effort
One command — npx -y @modelcontextprotocol/server-memory
USE CASES
01
Carrying context about a person or project between chats
Create the entity once with its type, then add observations as they come up rather than restating them each session.
02
Recalling what is known about a name that just came up
Search across names, types and observation text, then open the matching nodes to see how they connect.
03
Recording how people and organisations relate
Store the connection as a directed relation in active voice, so the graph answers 'who works where' without a full re-read.
04
Retracting something that is no longer true
Delete the single observation, or the relation, without touching the rest of what the entity holds.
05
Clearing out a subject entirely
Delete the entity and let its relations go with it, instead of leaving edges pointing at nothing.
9 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
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
9 tools when we connected.
Requires
npx on PATH
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 9 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @modelcontextprotocol/server-memoryMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}
