dowhy_mcp

lesong36/dowhy_mcp

3.3

If you are the rightful owner of dowhy_mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

DoWhy MCP v2.0 is a comprehensive server for rigorous causal inference using the Model Context Protocol.

Tools

Functions exposed to the LLM to take actions

Modeling Tools

Tools for causal graph construction and validation, structural and graphical causal models, and causal mechanism learning.

Causal Effect Estimation

Tools for backdoor, frontdoor, and IV identification, linear regression, PSM, doubly robust, DML, causal forests, and TMLE.

Causal Influence Quantification

Tools for Shapley value attribution, direct and total causal influence, and path-specific effects.

Root Cause Analysis

Tools for anomaly attribution, distribution change attribution, and causal chain tracing.

Counterfactual Analysis

Tools for individual and population counterfactuals, intervention simulation, and what-if scenario analysis.

Sensitivity Analysis

Tools for unobserved confounder analysis, comprehensive refutation tests, and E-value and tipping point analysis.

Causal Discovery

Tools for PC, GES, and FCM algorithms and structure learning from data.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources