Vector Store Scanner runs on your own machine — the client starts it, so there is no endpoint to ping. 314 installs a week from npm. Last commit 1 Nov 2026.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Today is the operative word: we check Vector Store Scanner every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 vector-store-scanner -- npx -y @guardbee/mcp-vector-store-scanner
{
"mcpServers": {
"vector-store-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-vector-store-scanner"
]
}
}
}
[mcp_servers.vector-store-scanner]
command = "npx"
args = ["-y", "@guardbee/mcp-vector-store-scanner"]
{
"mcpServers": {
"vector-store-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-vector-store-scanner"
]
}
}
}
{
"servers": {
"vector-store-scanner": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-vector-store-scanner"
]
}
}
}
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Curated & traceable AI venture data: verified funding events, org & founder profiles, US + China
Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Embedded graph database for agents: declare association rules once, edges maintain themselves.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Query your Supabase project: table rows, auth users, RPC. Endpoints per official docs.
Exposes the full Qdrant vector database API as 56 MCP tools, not just store/find.
Answers built from our own checks of this server.