Solr Vector Search MCP server

This Python package integrates Apache Solr with AI assistants like Claude through the Model Context Protocol (MCP). It enables powerful hybrid search capabilities, combining the precision of keyword search with the semantic understanding of vector search.

Getting Started

Prerequisites

• Python 3.10 or higher
• Docker and Docker Compose
• SolrCloud 9.x
• Ollama (for embedding generation)

Installation

Follow these steps to set up the Solr MCP server:

1. Clone the repository:

git clone https://github.com/username/solr-mcp.git
cd solr-mcp

2. Start SolrCloud with Docker:

docker-compose up -d

3. Set up the Python environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install poetry
poetry install

Indexing Sample Documents

Process and index the sample document to test the system:

python scripts/process_markdown.py data/bitcoin-whitepaper.md --output data/processed/bitcoin_sections.json
python scripts/create_unified_collection.py unified
python scripts/unified_index.py data/processed/bitcoin_sections.json --collection unified

Usage

Running the MCP Server

Start the MCP server with the following command:

poetry run python -m solr_mcp.server

Hybrid Search Capabilities

The Solr MCP integration provides several key features:

• Combined Search Approaches: Merges keyword search precision with vector search semantic understanding
• Vector Embeddings: Automatically generates embeddings for documents using Ollama with nomic-embed-text
• Unified Collections: Stores both document content and vector embeddings in the same collection

Performance Optimization

The system optimizes combined vector and SQL queries by:

1. Pushing SQL filters (WHERE clauses) down to the vector search stage
2. Only performing vector similarity calculations on documents that match SQL criteria
3. Improving performance for queries with selective filters, pagination, or large result sets

This approach significantly reduces computational overhead and network transfer by minimizing vector similarity calculations.

Configuration

The MCP server can be configured by modifying environment variables or configuration files. Refer to the detailed documentation for specific configuration options.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.