Qdrant RBAC
Role-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.
Open the source (opens github.com) https://github.com/fidonis/qdrant-mcp-rbac
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: QDRANT_JWT_SECRET. Use a key with the least access you can.
What it is
MCP servers from de.fidonis.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
oci package (streamable-http)
ghcr.io/fidonis/qdrant-mcp-rbac:0.4.2
From the server's entry in the official MCP Registry
Settings it asks for
OIDC_ISSUER_URLrequired · OIDC issuer / realm URL, e.g. https://kc.example.com/realms/myrealmOIDC_AUDIENCErequired · Expected aud claim of incoming access tokens, e.g. mcp-serverQDRANT_URLrequired · Qdrant HTTP endpoint, e.g. http://qdrant:6333QDRANT_JWT_SECRETsecret required · HS256 signing secret, at least 32 bytes; must equal Qdrant's service.api_key
Related
-
mcp-server-qdrant
MCP serversAn official Qdrant Model Context Protocol (MCP) server implementation
git clone https://github.com/qdrant/mcp-server-qdrant.git -
minima
MCP serversOn-premises conversational RAG with configurable containers
git clone https://github.com/Minima-AI-Inc/minima.git -
Zengram
MCP serversA Multi Agent Memory MCP That Connect Agents Across Systems and Machines
git clone https://github.com/ZenSystemAI/Zengram.git -
Qdrant Memory
MCP serversPersistent scoped Qdrant memory for agents, through four explicit stdio MCP tools.
qdrant-memory-mcp@0.3.5 -
mcp-qdrant
MCP serversRead-only Qdrant vector DB for AI agents — collections, info, browse points, count, search.
@infoinlet/mcp-qdrant@0.1.1 -
Qdrant MCP
MCP serversThe full Qdrant API as 58 MCP tools: plain-text semantic/BM25/hybrid search and a search advisor.
mcp-qdrant@2.12.0