Collective Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 29 May 2026.
MCP server for persistent, semantic memory across AI sessions
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
<script src="https://d3js.org/d3.v7.min.js"></script>
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add collective-memory -e 'OPENAI_API_KEY=<OPENAI_API_KEY>' -- npx -y collective-memory{
"mcpServers": {
"collective-memory": {
"command": "npx",
"args": [
"-y",
"collective-memory"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}[mcp_servers.collective-memory]
command = "npx"
args = ["-y", "collective-memory"]
env = { OPENAI_API_KEY = "<OPENAI_API_KEY>" }{
"mcpServers": {
"collective-memory": {
"command": "npx",
"args": [
"-y",
"collective-memory"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}{
"servers": {
"collective-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"collective-memory"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Put your own value in place of
<OPENAI_API_KEY> (OpenAI API key for generating embeddings).
The author’s registry entry marks it as required.
Alternatives to Collective Memory
same job, measured the same wayMCP server for Memanto - persistent semantic memory for any MCP-compatible agent
Cognitive memory for AI coding assistants — persistent memory across sessions
Open-source MCP memory server. Persistent, searchable, tiered memory across sessions.
MCP server for persistent, searchable memory for AI agents.
Persistent memory for AI assistants. Store, search, and recall across sessions.
Persistent memory for AI agents. Search, store, and recall across sessions.
Structured session journals for AI agents. Persistent memory across sessions.
An MCP server that provides persistent memory and context management across sessions
Collective Memory — questions
Answers built from our own checks of this server.