store_memoryLABSCO SUMMARY
Buckets are the unit, and the citation is the differentiator.
Plenty of memory servers return an answer; this one returns the memories and graph edges that produced it, which is what makes a wrong answer debuggable. Organising by bucket — work, personal, one per project — is not decoration either: retrieval is scoped to a bucket, and the MCP tool takes one at a time.
What it is
A hosted memory service reached over SSE. Memories go into named buckets; retrieval fuses BM25, vector search and a knowledge graph, reranks the result, and returns an answer with the memories that justified it.
What you get
- A fact stored, in a bucket you name or the default one —
store_memory - A natural-language question answered from stored memories, with synthesis and a per-memory explanation —
query_memory - A bucket's memories listed newest first, with
limitbetween 1 and 100 and a default of 20 —list_memories - The buckets that exist —
list_buckets - One memory deleted by id, or a whole bucket cleared —
delete_memory,clear_memories - Model calls routed through your own provider, so retrieval carries no inference markup
Requirements
A Lumetra account and an API key, sent as an Authorization: Bearer header to https://mcp.lumetra.io/mcp/sse. Claude.ai on the web and ChatGPT use OAuth instead and need no pasted key. There is no local installation. The free tier covers 10K stored memories and 50K retrievals per month with no credit card. One limit to plan around: the MCP query_memory tool takes a single bucket per call — multi-bucket fusion lives on the REST endpoint and in the SDKs.
Setup effort
One command plus a key — claude mcp add-json engram '{"type":"sse","url":"https://mcp.lumetra.io/mcp/sse","headers":{"Authorization":"Bearer <YOUR_API_KEY>"}}', then supply credentials
USE CASES
01
Carrying context between sessions
Store stable preferences and project facts as short declarative statements, then query before answering anything that depends on them.
02
Keeping projects from bleeding into each other
Give each project its own bucket so a query about one does not pull facts from another.
03
Checking why the agent said something
Read the memories and edges cited in the answer rather than trusting the synthesis.
04
Cleaning up after a project ends
Delete the memories that are wrong, or clear the whole bucket when the work is done.
6 tools
Listed in project docs. Your client may show a different list.
query_memorylist_memorieslist_bucketsdelete_memoryclear_memoriesBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Server setup
claude mcp add
Claude Code
TERMINAL
claude mcp add-json engram '{"type":"sse","url":"https://mcp.lumetra.io/mcp/sse","headers":{"Authorization":"Bearer <YOUR_API_KEY>"}}'Hosted endpoint
ENDPOINT URL
https://mcp.lumetra.io/mcp/sseAdd this hosted endpoint to your MCP client, then sign in.
MCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"engram": {
"url": "https://mcp.lumetra.io/mcp/sse",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}Windsurf
WINDSURF · JSON
{
"mcpServers": {
"engram": {
"serverUrl": "https://mcp.lumetra.io/mcp/sse",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}
