Qdrant
Qdrant MCP Server provides semantic search capabilities using a local Qdrant vector database and OpenAI embeddings, built by mhalder with comprehensive TypeScript implementation and 114 unit tests. The server automatically converts text documents to embeddings using OpenAI's models, stores them in a locally-running Qdrant instance via Docker for complete data privacy, and enables natural language search with metadata filtering using Qdrant's powerful filter syntax. It supports full collection lifecycle management (create, delete, info), document operations with automatic UUID normalization for string IDs, and both simple key-value and complex boolean filter expressions, making it valuable for building private knowledge bases, document search systems, and AI assistants that need semantic search without sending data to external vector database services.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/mhalder/qdrant-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Qdrant from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.