Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@JeffersonStats run a two-sample t-test on groups A and B"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
JeffersonStats is a powerful, high-performance statistical analysis server built on the FastMCP framework. It provides a comprehensive suite of statistical tools accessible via a clean, intuitive API. Whether you're performing basic descriptive statistics or advanced statistical tests, JeffersonStats delivers accurate results with minimal configuration.
Related MCP server: xtai-mcp-data-analysis
JeffersonStats offers a rich set of statistical capabilities:
Mean, median, mode, and range calculations
Standard deviation and variance
Quartiles and interquartile range (IQR)
Percentile and quantile calculations
Skewness and kurtosis analysis
Correlation coefficients (Pearson, Spearman, Kendall's tau)
Covariance calculations
Z-score transformations
T-tests (one-sample, independent, paired)
ANOVA (Analysis of Variance)
Chi-square tests
Mann-Whitney U test
Wilcoxon signed-rank test
Normality tests (Shapiro-Wilk)
Binomial tests
Linear regression
Confidence intervals (standard and bootstrap)
Outlier detection
Moving averages
Frequency tables
Comprehensive descriptive statistics summaries
High Performance: Built on optimized NumPy and SciPy libraries for fast computation
Easy Integration: Simple HTTP API that works with any programming language or platform
Comprehensive: Over 30 statistical tools in a single package
Reliable: Based on industry-standard statistical implementations
Containerized: Easy deployment with Docker
Scalable: Designed to handle large datasets efficiently
# Clone the repository
git clone https://github.com/yourusername/JeffersonStats.git
cd JeffersonStats
# Create a virtual environment (optional but recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Run the server
python mcpserver.py# Clone the repository
git clone https://github.com/yourusername/JeffersonStats.git
cd JeffersonStats
# Build the Docker image
docker build -t jeffersonstats:latest .
# Run the container
docker run -p 8080:8080 jeffersonstatsThe server will be available at http://localhost:8080.
JeffersonStats exposes its statistical tools through a MCP server using streamble-http transport. Here are some examples:
CherryStudio
VSCode
Cursor
WindSurf
BlackGoose
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Structured analysis API and remote MCP tool for text, JSON records and numeric series.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Educational MCP server with 17 math/stats tools, visualizations, and persistent workspace
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
