Qdrant MCP Server

Created By
hadva year ago
A Model Context Protocol (MCP) server implementation for RAG
Overview

What is Qdrant MCP Server for RAG?

Qdrant MCP Server for RAG is a Model Context Protocol (MCP) server implementation designed for Retrieval-Augmented Generation (RAG) using the Qdrant vector database.

How to use Qdrant MCP Server?

To use the Qdrant MCP Server, clone the repository, install dependencies, configure environment variables, and start the server. You can also deploy it using Docker.

Key features of Qdrant MCP Server?

  • Vector Search: Perform semantic searches over vector embeddings stored in Qdrant.
  • Customizable Parameters: Configure search parameters like limit and score threshold.
  • LLM Integration: Ready for integration with Claude Desktop and other MCP-compatible tools.

Use cases of Qdrant MCP Server?

  1. Conducting semantic searches in large datasets.
  2. Integrating with language models for enhanced data retrieval.
  3. Customizing search responses based on specific requirements.

FAQ from Qdrant MCP Server?

  • What is the prerequisite for using Qdrant MCP Server?

You need Node.js v16+, a Qdrant instance, and optionally an OpenAI API key for production embedding generation.

  • Can I use different vector databases?

Yes! The server supports both Qdrant and Chroma vector databases.

  • Is there a Docker deployment option?

Yes! You can build and run the server using Docker.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
hadv
Star
0
Language
TypeScript
License
MIT license
Tags

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago