Solr Vector Search

Bridges Apache Solr search indexes with vector embeddings for hybrid keyword and semantic document retrieval, enabling contextual searches against structured data repositories without direct database access

Solr MCP provides a bridge between AI assistants and Apache Solr search indexes, enabling powerful hybrid search capabilities that combine keyword precision with vector semantic understanding. Built by Allen Day, this Python implementation uses FastMCP to expose Solr's search functionality through a standardized protocol, with features including vector embeddings generation via Ollama (using nomic-embed-text), unified collections for storing both document content and embeddings, and Docker integration for easy deployment. The server is particularly valuable for workflows requiring advanced document retrieval from existing Solr indexes, allowing AI assistants to perform contextual searches against structured data repositories without direct database access.