Skip to main content
Glama

DoWhy MCP v2.0

by lesong36
MIT License

DoWhy MCP v2.0 - Rigorous Causal Inference Tools

Python 3.9+ DoWhy License: MIT Code style: black

๐ŸŽฏ Project Vision

DoWhy MCP v2.0 is a complete rewrite of the DoWhy MCP server, designed to provide rigorous, theoretically-grounded causal inference tools through the Model Context Protocol (MCP). This version matches the scientific rigor and theoretical depth of the official DoWhy library.

๐Ÿ”ฌ Theoretical Foundation

Built on the solid theoretical foundations of:

  • Structural Causal Models (SCM) - Pearl's causal hierarchy

  • Graphical Causal Models (GCM) - Modern causal discovery and inference

  • Potential Outcomes Framework - Rubin's causal model

  • Do-Calculus - Formal causal reasoning

๐Ÿš€ Key Features

โœ… What's New in v2.0

  • ๐Ÿงฎ Rigorous Statistical Inference: True Bootstrap confidence intervals, not noise simulation

  • ๐Ÿ” Comprehensive Sensitivity Analysis: Full suite of refutation tests and E-value analysis

  • ๐Ÿ“Š Complete Causal Toolkit: 42 specialized tools covering all DoWhy functionality

  • ๐ŸŽฏ Theoretical Rigor: Every method backed by solid causal inference theory

  • โšก Performance Optimized: Efficient implementation with proper error handling

  • ๐Ÿ“ˆ Advanced Visualization: Causal graphs, attribution plots, and diagnostic charts

๐Ÿ› ๏ธ Complete Tool Categories

  1. Modeling Tools (6 tools)

    • Causal graph construction and validation

    • Structural and Graphical Causal Models

    • Causal mechanism learning

  2. Causal Effect Estimation (10 tools)

    • Backdoor, frontdoor, and IV identification

    • Linear regression, PSM, doubly robust, DML

    • Causal forests and TMLE

  3. Causal Influence Quantification (6 tools)

    • Shapley value attribution

    • Direct and total causal influence

    • Path-specific effects

  4. Root Cause Analysis (5 tools)

    • Anomaly attribution

    • Distribution change attribution

    • Causal chain tracing

  5. Counterfactual Analysis (6 tools)

    • Individual and population counterfactuals

    • Intervention simulation

    • What-if scenario analysis

  6. Sensitivity Analysis (6 tools)

    • Unobserved confounder analysis

    • Comprehensive refutation tests

    • E-value and tipping point analysis

  7. Causal Discovery (3 tools)

    • PC, GES, and FCM algorithms

    • Structure learning from data

๐Ÿ“‹ Installation

# Install from source (development) git clone https://github.com/dowhy-mcp/dowhy-mcp-v2.git cd dowhy-mcp-v2 pip install -e ".[dev]" # Install from PyPI (when released) pip install dowhy-mcp-v2

๐Ÿ”ง Quick Start

from dowhy_mcp_v2 import DoWhyCausalAnalyzer # Initialize analyzer analyzer = DoWhyCausalAnalyzer() # Estimate causal effect with full rigor result = analyzer.estimate_causal_effect( data="data.csv", treatment="intervention", outcome="result", confounders=["age", "gender", "income"], method="doubly_robust", bootstrap_samples=1000, sensitivity_analysis=True ) # Get comprehensive results print(f"Causal Effect: {result.causal_effect:.4f}") print(f"95% CI: [{result.confidence_interval[0]:.4f}, {result.confidence_interval[1]:.4f}]") print(f"P-value: {result.p_value:.4f}") print(f"Robustness Score: {result.robustness_score:.2f}")

๐Ÿ—๏ธ Architecture

DoWhy MCP v2.0 โ”œโ”€โ”€ Core Engine # Causal inference engine โ”‚ โ”œโ”€โ”€ Model Builder # SCM/GCM construction โ”‚ โ”œโ”€โ”€ Inference Engine # Causal reasoning โ”‚ โ””โ”€โ”€ Validation Framework # Result verification โ”œโ”€โ”€ Tool Modules # 42 specialized tools โ”‚ โ”œโ”€โ”€ Modeling # Graph and model tools โ”‚ โ”œโ”€โ”€ Estimation # Effect estimation โ”‚ โ”œโ”€โ”€ Attribution # Influence quantification โ”‚ โ”œโ”€โ”€ Root Cause # Anomaly analysis โ”‚ โ”œโ”€โ”€ Counterfactual # What-if analysis โ”‚ โ”œโ”€โ”€ Sensitivity # Robustness testing โ”‚ โ””โ”€โ”€ Discovery # Structure learning โ””โ”€โ”€ MCP Interface # Protocol integration

๐Ÿ“Š Comparison with v1.0

Feature

v1.0

v2.0

Theoretical Rigor

Basic

โœ… Complete

Bootstrap CI

โŒ Fake noise

โœ… True Bootstrap

Sensitivity Analysis

โŒ Simplified

โœ… Comprehensive

Causal Graphs

โŒ Limited

โœ… Full Support

Tool Count

4 basic

42 rigorous

Statistical Tests

โŒ Missing

โœ… Complete Suite

Error Handling

โŒ Basic

โœ… Robust

Documentation

โŒ Minimal

โœ… Comprehensive

๐Ÿงช Testing & Validation

  • Unit Tests: 95%+ coverage with rigorous testing

  • Integration Tests: End-to-end workflow validation

  • Benchmark Tests: Performance and accuracy benchmarks

  • Theoretical Tests: Validation against known causal results

๐Ÿ“š Documentation

๐Ÿค Contributing

We welcome contributions! Please see our Contributing Guide for details.

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

๐Ÿ™ Acknowledgments

๐Ÿ“ž Support


DoWhy MCP v2.0 - Where Rigorous Science Meets Practical Application

-
security - not tested
A
license - permissive license
-
quality - not tested

A server providing rigorous causal inference tools through the Model Context Protocol (MCP), offering 42 specialized causal analysis tools that cover modeling, effect estimation, attribution, root cause analysis, counterfactuals, and sensitivity analysis.

  1. ๐ŸŽฏ Project Vision
    1. ๐Ÿ”ฌ Theoretical Foundation
      1. ๐Ÿš€ Key Features
        1. โœ… What's New in v2.0
        2. ๐Ÿ› ๏ธ Complete Tool Categories
      2. ๐Ÿ“‹ Installation
        1. ๐Ÿ”ง Quick Start
          1. ๐Ÿ—๏ธ Architecture
            1. ๐Ÿ“Š Comparison with v1.0
              1. ๐Ÿงช Testing & Validation
                1. ๐Ÿ“š Documentation
                  1. ๐Ÿค Contributing
                    1. ๐Ÿ“„ License
                      1. ๐Ÿ™ Acknowledgments
                        1. ๐Ÿ“ž Support

                          Related MCP Servers

                          • A
                            security
                            A
                            license
                            A
                            quality
                            A beginner-friendly Model Context Protocol (MCP) server that helps users understand MCP concepts, provides interactive examples, and lists available MCP servers. This server is designed to be a helpful companion for developers working with MCP. Also comes with a huge list of servers you can install.
                            Last updated -
                            3
                            16
                            63
                            Apache 2.0
                          • A
                            security
                            F
                            license
                            A
                            quality
                            An all-in-one Model Context Protocol (MCP) server that connects your coding AI to numerous databases, data warehouses, data pipelines, and cloud services, streamlining development workflow through seamless integrations.
                            Last updated -
                            3
                            • Apple
                            • Linux
                          • -
                            security
                            F
                            license
                            -
                            quality
                            A comprehensive Model Context Protocol (MCP) server implementing the latest MCP specification with tools, resources, prompts, and enhanced sampling capabilities that features HackerNews and GitHub API integrations for AI-powered analysis.
                            Last updated -
                            334
                          • -
                            security
                            A
                            license
                            -
                            quality
                            Model Context Protocol (MCP) server that provides AI assistants with advanced web research capabilities, including Google search integration, intelligent content extraction, and multi-source synthesis.
                            Last updated -
                            11
                            4
                            MIT License

                          View all related MCP servers

                          MCP directory API

                          We provide all the information about MCP servers via our MCP API.

                          curl -X GET 'https://glama.ai/api/mcp/v1/servers/lesong36/dowhy_mcp'

                          If you have feedback or need assistance with the MCP directory API, please join our Discord server