MCP AutoMem is listed as active in the registry but did not answer our last check. 101 installs a week from npm. Last commit 26 Aug 2026.
Graph-vector memory for AI assistants using FalkorDB and Qdrant
What the code does
We read the source, 21 h ago · rules 3dff92dd89df
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.
const child = spawn(command, args, { stdio: 'ignore', detached: true });
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
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add mcp-automem --transport http https://{endpoint}/mcp{
"mcpServers": {
"mcp-automem": {
"url": "https://{endpoint}/mcp"
}
}
}[mcp_servers.mcp-automem]
url = "https://{endpoint}/mcp"{
"mcpServers": {
"mcp-automem": {
"url": "https://{endpoint}/mcp"
}
}
}{
"mcpServers": {
"mcp-automem": {
"url": "https://{endpoint}/mcp"
}
}
}This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://{endpoint}/mcp | streamable-http | answering | 0 ms | 1 min ago |
| https://{endpoint}/mcp/sse | sse | answering | 0 ms | 1 min ago |
Alternatives to MCP AutoMem
same job, measured the same wayPersistent memory and knowledge graph for AI assistants — keyword + vector + graph search.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
MCP AutoMem — questions
Answers built from our own checks of this server.