Qdrant Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 1 918 installs a week from pypi. Last commit 16 Oct 2026.
Persistent scoped Qdrant memory for agents, through four explicit stdio MCP tools.
We read the source, 10 h ago · rules ccca72095570
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.
return subprocess.check_output(['git', '-C', str(root), *args], text=True, stderr=subprocess.DEVNULL).strip()
const result = spawnSync(executable, args, { env, timeout, encoding: 'utf8', windowsHide: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 qdrant-memory -- uvx qdrant-memory-mcp
{
"mcpServers": {
"qdrant-memory": {
"args": [
"qdrant-memory-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.qdrant-memory]
command = "uvx"
args = ["qdrant-memory-mcp"]
{
"mcpServers": {
"qdrant-memory": {
"args": [
"qdrant-memory-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"qdrant-memory": {
"args": [
"qdrant-memory-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
QDRANT_URL (Optional remote Qdrant endpoint when configured for server/cloud mode.), QDRANT_API_KEY (Optional Qdrant credential for configured remote storage.), EMBEDDING_API_KEY (Optional credential for the configured embedding provider.).
The author declared them in the registry entry; get the values from the project itself.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.
Answers built from our own checks of this server.