BFSI & FinTech ApexSubmitted July 26, 2026

SanctionDesk: An Agentic AI Framework for Explainable Loan Underwriting using NitroStack MCP

An MCP app on the Model Context Protocol built by Apex at the Amrita University Coimbatore NitroStack × MCP To The Moon hackathon and deployed on NitroStack.

About this project

A NitroStack MCP-based Agentic Underwriting Framework integrating enterprise intelligence with deterministic policy evaluation for explainable, auditable, and counterfactual loan decisions.

BFSI & FinTech track

Build AI solutions for banking, payments, insurance, fraud detection, lending, and financial inclusion.

Source code

Team Apex

  • Sharvesh SivagnanamLead

  • Rajashree T

  • Ravishanmugam K

  • Dokku Naga Shiva

← All Amrita University Coimbatore projects

Frequently asked questions

What does SanctionDesk: An Agentic AI Framework for Explainable Loan Underwriting using NitroStack MCP do?
A NitroStack MCP-based Agentic Underwriting Framework integrating enterprise intelligence with deterministic policy evaluation for explainable, auditable, and counterfactual loan decisions.
Who built SanctionDesk: An Agentic AI Framework for Explainable Loan Underwriting using NitroStack MCP?
SanctionDesk: An Agentic AI Framework for Explainable Loan Underwriting using NitroStack MCP was built by team Apex at the Amrita University Coimbatore NitroStack × MCP To The Moon hackathon, in the BFSI & FinTech track.
What is an MCP app and how is it built?
An MCP app is an application built on the Model Context Protocol — an open standard that lets AI agents connect to tools, data, and APIs. This project exposes MCP tools and resources that agentic AI systems can call. It was built and deployed on NitroStack, the full-stack platform for shipping MCP apps and servers.