MCP server that exposes the credit scoring model's deterministic tools (probability of default, SHAP explanations, typicality check, financial ratios) to AI agents, enabling natural language credit risk assessment.
A production-grade MCP server that exposes real-time banking data replicated via Oracle GoldenGate CDC as structured tools for AI agents, enabling read, score, and write operations on customer, account, transaction, and alert data.
Enables users to train and compare breast-cancer classification models, obtain sample inputs, make predictions with Logistic Regression or KNN, evaluate metrics, select the best model, generate SHAP explanations, and export Parquet audit logs through MCP tools.
Deploys an MCP server on Azure Container Apps that exposes Azure ML managed online endpoints as tools, enabling AI agents like Azure AI Foundry to invoke machine learning models via natural language.
Enables MCP-compatible applications to manage and run local or cloud language models, perform chat, text generation, and embeddings, and use web search and fetch tools through MCP.