Back to Home
No-Smoke icon

qdrant-mcp-server

Verified Safe

by No-Smoke

Overview

Provides semantic search and code vectorization capabilities using Qdrant vector database and various embedding providers, suitable for AI-assisted development and knowledge base management.

Installation

Run Command
node build/index.js

Environment Variables

  • QDRANT_URL
  • QDRANT_API_KEY
  • EMBEDDING_PROVIDER
  • TRANSPORT_MODE
  • HTTP_PORT
  • PROMPTS_CONFIG_FILE
  • EMBEDDING_MODEL
  • EMBEDDING_DIMENSIONS
  • EMBEDDING_BASE_URL
  • EMBEDDING_MAX_REQUESTS_PER_MINUTE
  • EMBEDDING_RETRY_ATTEMPTS
  • EMBEDDING_RETRY_DELAY
  • OPENAI_API_KEY (required if EMBEDDING_PROVIDER=openai)
  • COHERE_API_KEY (required if EMBEDDING_PROVIDER=cohere)
  • VOYAGE_API_KEY (required if EMBEDDING_PROVIDER=voyage)
  • CODE_CHUNK_SIZE
  • CODE_CHUNK_OVERLAP
  • CODE_ENABLE_AST
  • CODE_BATCH_SIZE
  • CODE_CUSTOM_EXTENSIONS
  • CODE_CUSTOM_IGNORE
  • CODE_DEFAULT_LIMIT
  • CODE_ENABLE_HYBRID

Security Notes

The server includes path validation (`validatePath`) to prevent directory traversal attacks when indexing codebases. For HTTP transport, the README provides critical security warnings regarding deployment (HTTPS, authentication, firewalls, reverse proxy). Rate limiting is implemented for the HTTP server to mitigate abuse. The `containsSecrets` function is a feature to detect potential secrets within *indexed user codebases*, not within the server's own codebase, which is a good safety measure. No 'eval' or obvious hardcoded secrets were found in the provided source.

Similar Servers

Stats

Interest Score0
Security Score8
Cost ClassHigh
Avg Tokens50000
Stars0
Forks0
Last Update2026-01-17

Tags

semantic searchvector databasecode searchembeddingsRAGAI-assisted developmentqdrantollama