semantic-postgres-mcp

semantic-postgres-mcp

3.1

If you are the rightful owner of semantic-postgres-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol (MCP) server that enables AI assistants like Claude to perform semantic search on PostgreSQL databases.

The Semantic PostgreSQL MCP Server is designed to connect AI assistants, such as Claude, to PostgreSQL databases, enabling semantic search capabilities. This server leverages the Model Context Protocol (MCP), an open standard developed by Anthropic, to facilitate seamless interaction between AI models and external systems like databases. By using vector embeddings, the server can understand the semantic meaning of database structures, allowing users to execute natural language queries and receive context-aware responses. The server supports hybrid search, combining keyword matching with semantic understanding, and does not require any modifications to existing database schemas. It integrates easily with Claude Desktop and requires PostgreSQL 13+ with the pgvector extension, Node.js 18+, and an OpenAI API key for generating embeddings.

Features

  • Vector-based semantic search: Uses OpenAI's embeddings to understand semantic meaning.
  • Metadata-driven: Stores rich descriptions of tables and columns in vector format.
  • No schema modification needed: Your existing database tables remain unchanged; metadata is stored separately.
  • Simple integration with Claude Desktop: Easy configuration with Claude Desktop.