avbbc Submit a tool

Qdrant MCP

Searches a Qdrant collection and returns matching payloads with scores. It is the retrieval half of a RAG system exposed as a tool: the agent asks a question, gets passages. What it does not…

Official stdio Verified 2026-11-12 databasevectorragsearch

Use it for

Searching a vector collection the team already maintains

Skip it if

Building the embedding pipeline — this is the retrieval surface, not the indexer

What it is

Searches a Qdrant collection and returns matching payloads with scores. It is the retrieval half of a RAG system exposed as a tool: the agent asks a question, gets passages. What it does not do is decide whether those passages answer the question, which is the source of most retrieval failures.

Install

Terminal
uvx mcp-server-qdrant

Client configuration

Paste this into your MCP client config, then restart the client.

MCP client config (JSON)
{
  "mcpServers": {
    "avbbc": {
      "command": "npx",
      "args": ["-y", "uvx mcp-server-qdrant"]
    }
  }
}

Overlapping servers

All servers
  • 01
    ClickHouse MCPCommunity

    Runs SQL against a ClickHouse database with a read-only user: table listing, schema inspection, and query execution. The natural fit is event data where an agent can…

    #database#analytics#sql
    Pythonstdio
  • 02
    DuckDB MCPCommunity

    Opens a local DuckDB database and exposes SQL over it, including files as views. That makes it the cheapest way to let an agent analyse a data dump on a laptop: no w…

    #database#analytics#local
    Pythonstdio
  • 03
    Pinecone MCPCommunity

    Runs similarity queries against a Pinecone index and returns matches with metadata. The hosted model means the agent needs a key and an index name, and nothing else …

    #database#vector#rag
    TypeScriptstdio

Tools that use this server

All tools

Skills built around it

All skills