NRTSearch MCP Server
Enables natural language querying of Lucene/NRTSearch indexes through GitHub Copilot Chat, allowing AI-assisted search with support for Boolean, phrase, range, wildcard, and fuzzy queries.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
NRTSearch MCP Server
Production-ready Model Context Protocol (MCP) server for Lucene/NRTSearch, with first-class support for AI assistants like GitHub Copilot and Claude.
Features
Exposes NRTSearch/Lucene search as a robust MCP server for AI tools
Accepts any Lucene query (Boolean, phrase, range, wildcard, fuzzy, etc.)
Structured logging, retries, and highlight support
Pure unit-testable search logic with full test coverage
Easy integration with GitHub Copilot, Claude Desktop, and other MCP clients
Modern Python packaging and configuration (Pydantic, pyproject.toml)
Related MCP server: AXYS MCP Lite
Quick Start
git clone https://github.com/tvergilio/nrtsearch-mcp-server.git
cd nrtsearch-mcp-server
./quickstart.shThis will:
Install all dependencies (including MCP SDK)
Start the server on the configured port
Usage
CLI / Manual
After installation, you can start the server with either:
# Using the Python module
python -m nrtsearch_mcp.server
# Or, if installed via pip/pipx, use the CLI entrypoint:
nrtsearch-mcpWith GitHub Copilot (VS Code)
Install VS Code and GitHub Copilot
Add
nrtsearch-mcpas a Model Context Provider in VS Code settings (see.vscode/settings.json)Start the server (
./quickstart.shornrtsearch-mcp)Use Copilot Chat to query your Lucene indexes in natural language
Configuration
The server is configured via environment variables and/or a JSON config file. By default, it looks for:
NRTSEARCH_MCP_CONFIGenv var (path to config)./config.jsonin the current directory~/nrtsearch-mcp-config.jsonin your home directory
Example config:
{
"nrtsearch_connection": {
"host": "localhost",
"port": 8000,
"use_https": false
},
"log_level": "INFO"
}Key environment variables:
LOG_LEVEL(default: INFO)NRTSEARCH_MCP_CONFIG(optional config path)
API: Search Tool
The main tool is nrtsearch/search:
Parameters:
index(str): Index name (e.g.yelp_reviews_staging)queryText(str): Full Lucene query (e.g.text:(irish AND pub AND (texas OR tx)))topHits(int, default 10): Number of results (1-100)retrieveFields(list, optional): Fields to return (default:["text", "stars"])highlight(bool, optional): Highlight matches
Returns:
List of hits:
{score, stars, text}
Lucene Query Examples:
text:(irish AND pub AND (texas OR tx))text:"great coffee"stars:[4 TO 5] AND text:(vegan AND brunch)
Testing
Run all tests (unit, no server needed):
pytest -vTests cover:
Success, empty, and multiple hits
Error handling (HTTP, network, malformed, missing fields)
Retry logic
Highlight and custom fields
Input validation
Project Structure
nrtsearch-mcp-server/
├── nrtsearch_mcp/
│ ├── server.py # Main MCP server and search logic
│ ├── settings.py # Pydantic config
│ └── ...
├── tests/ # Unit tests
├── quickstart.sh # One-step install & run
├── requirements.txt # Python dependencies
├── pyproject.toml # Packaging/metadata
└── ...License
Apache License 2.0. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search your knowledge bases from any AI assistant using hybrid RAG.
Read-only search over the Vocenya AI receptionist API docs and endpoints, with code samples.
Read-only search over the aidata.stream documentation, blog, changelog, pricing and FAQ.
Search and query nTop's knowledge base and engineering guides from AI applications.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI systems to perform full-text and semantic search operations over structured/unstructured data in Azure Cognitive Search, with capabilities for document indexing and management through natural language.326 npm4ISC
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search through structured databases and unstructured content (documents, videos, files) using natural language queries with semantic understanding.MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to search, analyze, and interact with Elasticsearch through natural language.18Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search, query, and manage Azure AI Search indexes using full-text, semantic, and vector search, alongside index and document operations.MIT