solr-mcp
If you are the rightful owner of solr-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 Python package for accessing Apache Solr indexes via Model Context Protocol (MCP), enabling AI assistants to perform advanced search queries.
Solr MCP is a Python package designed to facilitate the integration of Apache Solr indexes with AI assistants through the Model Context Protocol (MCP). This package allows for powerful search capabilities by combining keyword and vector search methods. It supports the generation of vector embeddings using Ollama with nomic-embed-text, and stores both document content and vector embeddings in unified collections. The package is optimized for performance, especially in handling large datasets and complex queries, by pushing SQL filters to the vector search stage. It also offers easy setup through Docker and docker-compose, making it accessible for developers to deploy and manage.
Features
- MCP Server: Implements the Model Context Protocol for integration with AI assistants
- Hybrid Search: Combines keyword search precision with vector search semantic understanding
- Vector Embeddings: Generates embeddings for documents using Ollama with nomic-embed-text
- Unified Collections: Store both document content and vector embeddings in the same collection
- Optimized Vector Search: Efficiently handles combined vector and SQL queries by pushing down SQL filters to the vector search stage
