TC
ToolCompared
MCP Server

Qdrant MCP Server

by Qdrant

Connect models to a Qdrant vector database for semantic memory.

OfficialPythonDatabases
View RepositoryDocumentation

About Qdrant

Acts as an MCP server providing a semantic memory layer on top of the Qdrant vector search engine. Includes 'qdrant-store' and 'qdrant-find' tools for storing and retrieving information. Supports stdio and SSE transport protocols and is compatible with MCP-enabled clients like Cursor and Claude.

Tags

vector-databasesemantic-searchmemoryembeddings

How to install Qdrant

Add the following entry to your MCP client config (e.g. claude_desktop_config.json or .mcp.json). Refer to the official repository for the exact command, package name, and required environment variables.

{
  "mcpServers": {
    "qdrant": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-qdrant"]
    }
  }
}

Example shape only — see the repository for the canonical install command.

Related MCP servers in Databases

Postgres MCP
Anthropic

Run read-only SQL queries against a Postgres database.

SQLite MCP
Anthropic

Query and modify a local SQLite database file.

ClickHouse
ClickHouse

Read-only SQL access to ClickHouse for analytics workloads.

Neo4j
Neo4j

Natural-language queries over Neo4j graph databases.

← Back to MCP directory