Click on "Deploy 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., "@genpark-hypothesis-welch-t-test-statistical-evaluator-skill Run a Welch's t-test on my A/B test conversion data"
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.
genpark-hypothesis-welch-t-test-statistical-evaluator-skill delivers zero-dependency, mathematically rigorous statistical modeling, time-series forecasting, and anomaly detection primitives engineered strictly using Python 3.9+ standard library.
Zero External Dependencies: Operates exclusively via pure Python (math, random, statistics, json). Zero pip install overhead, zero numpy/scipy compilation failures.
Enterprise Statistical Invariants: Implements formal Holt linear smoothing, modified Z-score & Tukey IQR anomaly bounds, Welch's t-test p-value estimations, multivariate linear regression via gradient descent, and Power Iteration PCA dimensionality reduction.
Native Anthropic MCP Protocol: Compliant with standard JSON-RPC 2.0 stdio MCP specifications for Claude Desktop, Cursor, and Windsurf.
Related MCP server: genpark-linear-regression-gradient-descent-engine-skill
flowchart TD
DataStream["Time-Series & Multidimensional Numerical Stream"] --> AnomalyDetector["Statistical Z-Score & IQR Anomaly Detector"]
AnomalyDetector -->|Outlier Detected| FlagAnomaly["Flag Outlier & Alert Telemetry"]
AnomalyDetector -->|Clean Stream| ModelingBranch{"Analytical Objective"}
ModelingBranch -->|Trend Forecasting| HoltForecaster["Holt Linear Exponential Smoothing Forecaster"]
ModelingBranch -->|Supervised Fitting| LinearRegression["Multivariate Gradient Descent Regression Engine"]
ModelingBranch -->|Hypothesis Testing| WelchTest["Welch's Two-Sample T-Test Evaluator"]
ModelingBranch -->|Dimensionality Reduction| PCAReducer["Power Iteration SVD/PCA Dimension Reducer"]
HoltForecaster --> Synthesis["Agent Synthesis & Statistical Report"]
LinearRegression --> Synthesis
WelchTest --> Synthesis
PCAReducer --> Synthesisfrom client import HypothesisWelchTTestEvaluator
# Initialize engine
engine = HypothesisWelchTTestEvaluator()
# Execute self-testing benchmark suite
result = engine.run_benchmark_welch_t_test()
print("Execution Result:", result)Add to your claude_desktop_config.json or cursor.json:
{
"mcpServers": {
"genpark-hypothesis-welch-t-test-statistical-evaluator-skill": {
"command": "python",
"args": ["-u", "/path/to/genpark-hypothesis-welch-t-test-statistical-evaluator-skill/mcp_server.py"]
}
}
}This skill contains pre-configured smithery.yaml and pyproject.toml manifests. Install directly via pip:
pip install git+https://github.com/alphaparkinc/genpark-hypothesis-welch-t-test-statistical-evaluator-skill.gitThis server cannot be deployed
Structured analysis API and remote MCP tool for text, JSON records and numeric series.
The statistical analyst in your AI chat — validated, citable, re-runnable analysis of your data.
Connect your ads, shop, analytics, social, CRM and finance platforms once, then let Claude, ChatGPT, Cursor or any MCP client read, join and explain your numbers. Public statistics from the World Bank, IMF, Eurostat, OECD, WHO and SEC filings come as context, searchable and chartable from the same tools. Read-only by design, every number carries its source.
Exact statistics & probability: distributions, hypothesis tests, CIs, Bayesian updates, regression.
