store_memoryLABSCO SUMMARY
Old instructions stop outranking new ones.
Ordinary memory servers return whatever is semantically closest, which means a stale note can beat the correction that replaced it. Here every store is checked for conflicts first, memories carry an authority tier, and superseded ones are marked with a typed edge — so retrieval returns what is current rather than what is nearest.
What it is
A memory server for Claude Code and other MCP agents that adds three things to plain vector recall: authority weighting by priority tier, conflict detection before every store, and typed relationship edges between memories.
What you get
- Memories stored with a priority tier — high, medium or low — each carrying the authority weight retrieval ranks by
- Retrieval that weighs authority rather than semantic closeness alone
- Conflicts checked before a store, and resolved by authority
- Superseded memories marked as such and linked, instead of left to compete
- Typed edges added between memories, and the related ones walked
- Memories updated and deleted
Requirements
A recent Python — pip install mcp-memory-graph — and a path for the SQLite database it writes, set in the client configuration.
Setup effort
One command — pip install mcp-memory-graph
USE CASES
01
Making a correction actually stick
Check for conflicts before storing, then store the new instruction at a tier above the old one so retrieval stops preferring the stale version.
02
Recalling a project decision months later
Retrieve on the topic and walk the related memories, so the decision arrives with the reasoning that was attached to it.
03
Keeping a standing rule above a passing remark
Store the rule at high priority and the aside at low. The tiers are what decide the tie when both match the query.
04
Connecting facts that only mean something together
Add a typed edge between them, then walk the edges at retrieval time rather than hoping both surface from the same query.
05
Clearing out what is no longer true
Run conflict detection to find the duplicates and contradictions, then delete the entries that lost.
8 tools
Listed in project docs. Your client may show a different list.
retrieve_memoriescheck_conflictsupdate_memorydelete_memoryadd_memory_edgeget_related_memorieslist_memoriesBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
pip on PATH
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install mcp-memory-graphMCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"mcp-memory-graph": {
"type": "stdio",
"command": "mcp-memory-graph",
"env": {
"MEMORY_GRAPH_DB_PATH": "<YOUR_MEMORY_GRAPH_DB_PATH>"
}
}
}
}Claude Code — local build
CLAUDE CODE — LOCAL BUILD · JSON
{
"mcpServers": {
"mcp-memory-graph": {
"type": "stdio",
"command": "python",
"args": [
"<YOUR_PATH_TO_MCP_MEMORY_GRAPH>/server.py"
],
"env": {
"MEMORY_GRAPH_DB_PATH": "<YOUR_MEMORY_GRAPH_DB_PATH>"
}
}
}
}
