get_dataset_metadataLABSCO SUMMARY
Start at the metadata, then ask.
Every analysis tool takes a schemaId, so the first call is always the metadata one — that is the documented order and skipping it is where the tools fail. The credentials are Lumenore's, requested from their support, and the analytics run on Lumenore's backend, so the server is a thin local proxy: it processes in memory and stores nothing, but the data leaves your machine for Lumenore either way.
What it is
An MCP server over Lumenore's analytics platform. It converts a natural-language question into structured data against a Lumenore dataset, and offers six further tools that run specific analyses — trends, predictions, outliers, correlations, change detection and Pareto — over the same datasets.
What you get
- The available datasets and their schema IDs, which every other call needs —
get_dataset_metadata - A question in English turned into structured data for one
schemaId—nlq_to_data - Temporal patterns and forecasts —
get_trend_data,get_prediction_data - Anomalies, relationships and pattern shifts —
get_outlier_data,get_correlation_data,get_change_data - 80/20 impact analysis —
get_pareto_data - A consistent envelope on every tool:
statusissuccess,validation_errororerror, so a failed call is distinguishable from an empty answer
Requirements
Lumenore client credentials — LUMENORE_CLIENT_ID and LUMENORE_SECRET, obtained from Lumenore support — in a .env file, plus SERVER_URL if your instance is not the default https://preview.lumenore.com. Python 3.13+, pip install -r requirements.txt, then python main.py. The server listens on port 8080 and clients connect to http://localhost:8080/mcp over Streamable HTTP; the MCP connection itself takes no auth, since the credentials are used server-side against Lumenore.
Setup effort
Build from source — git clone https://github.com/Lumenore-Platform/lumenore-mcp.git
USE CASES
01
Answering a business question without building a report
Ask in English against a dataset and get structured data back instead of assembling a dashboard.
02
Explaining why a number moved
Pull the trend for the period, then look for a change point in the same series.
03
Finding the accounts that matter most
Run the 80/20 analysis rather than sorting an export by hand.
04
Spotting outliers in customer behaviour
Ask for unusual values in the dataset and follow up with the factors that correlate with them.
05
Forecasting next quarter from the same data
Generate the prediction in the conversation where the historical figures were just read.
8 tools
Listed in project docs. Your client may show a different list.
nlq_to_dataget_trend_dataget_prediction_dataget_outlier_dataget_correlation_dataget_change_dataget_pareto_dataBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
Python 3.13+
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/Lumenore-Platform/lumenore-mcp.git
cd lumenore-mcp
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your client credentials (LUMENORE_CLIENT_ID and LUMENORE_SECRET)
python main.pyMCP Clients
Any MCP client
URL: http://localhost:8080/mcp
Transport: Streamable HTTP
