create_entitiesLABSCO SUMMARY
Memory you can inspect, not a vector blob.
Facts go in as named entities, typed relations and one-fact observations, which means you can read the graph back and see exactly what the assistant believes — and delete a single wrong observation without disturbing the rest.
What it is
An MCP server implementing persistent memory as a local knowledge graph on the Kuzu embedded graph database. Memory is modelled as entities with a type, relations written in active voice, and observations that hold one fact each.
What you get
- Entities created with a name, a type and a list of observations
- Relations created between entities in active voice, with duplicates skipped
- Observations added to and removed from existing entities
- Entities and relations deleted
- The whole graph read back
- Nodes searched by query, and named nodes opened in full
- Tags for cross-cutting classification of entities and observations, with an optional category and description
Requirements
The graph lives in a local Kuzu embedded database, so it stays on your machine. Entity names are the identifier: creating one that already exists is ignored rather than duplicated.
Setup effort
One command — npx -y @deanacus/knowledge-graph-mcp
USE CASES
01
Giving an assistant memory that survives the session
Create the entities and the relations between them once, then read them back next time.
02
Correcting one wrong fact
Delete that observation and leave the entity and its other observations alone.
03
Adding what you learned today to what it already knew
Attach new observations to the existing entity rather than making a second one.
04
Finding what it knows about a person or a project
Search nodes by query, then open the ones you want in full.
05
Recording how two things are connected
Create the relation in active voice instead of burying it inside a sentence.
06
Removing someone or something entirely
Delete the entity along with the relations that pointed at it.
15 tools
Listed in project docs. Your client may show a different list.
create_relationsadd_observationsdelete_entitiesdelete_observationsdelete_relationsread_graphsearch_nodesopen_nodestag_entitytag_observationget_entities_by_tagget_all_tagsget_tag_usageremove_tags_from_entityBEFORE YOU INSTALL
What to know first
Tools you get
15 tools named in the project's documentation.
Requires
npx on PATH
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @deanacus/knowledge-graph-mcpMCP Clients
Any MCP client — npx
ANY MCP CLIENT — NPX · JSON
{
"mcpServers": {
"knowledge-graph": {
"command": "npx",
"args": [
"-y",
"@deanacus/knowledge-graph-mcp",
"<YOUR_PATH_TO_KNOWLEDGE_GRAPH>"
]
}
}
}<YOUR_PATH_TO_KNOWLEDGE_GRAPH> is where you want your knowledge graph stored. It is the database file, and the server creates it there if it does not exist yet.
VS Code
VS CODE · JSON
{
"servers": {
"knowledge-graph": {
"command": "npx",
"args": [
"-y",
"@deanacus/knowledge-graph-mcp",
"<YOUR_PATH_TO_KNOWLEDGE_GRAPH>"
]
}
}
}<YOUR_PATH_TO_KNOWLEDGE_GRAPH> is where you want your knowledge graph stored. It is the database file, and the server creates it there if it does not exist yet.
