Skip to main content
Glama
Yogeshwara7

Loan MCP Server

by Yogeshwara7
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Loan MCP Server

A Model Context Protocol (MCP) server that exposes read and analytics tools for a Loan Management System backed by Microsoft Dataverse. It can be consumed by MCP clients (Claude Desktop, Copilot Studio) over stdio or HTTP, and includes an optional WhatsApp assistant.

Features

  • 12 loan tools: lookups, search, timeline, eligibility, officer workload and portfolio analytics.

  • Two transports: stdio (Claude Desktop) and Streamable HTTP (Copilot Studio / remote clients), JSON-RPC 2.0.

  • Optional WhatsApp assistant via Twilio + an LLM.

  • Microsoft Entra ID authentication (client credentials); Dataverse Web API v9.2.

  • TypeScript, Node.js 22+, structured logging, typed error handling.

Related MCP server: dataverse-mcp-server

Tools

Tool

Input

Description

GetLoanSummary

referenceNumber

Full loan summary

GetLoanStatus

referenceNumber

Status, eligibility, officer, review flag

SearchLoansByPhone

phoneNumber

Loans for a phone number

GetApplicantHistory

applicantEmail

Applications for an applicant

TrackLoanTimeline

referenceNumber

Milestone timeline

ExplainEligibility

referenceNumber

Eligibility explanation

GetRequiredDocuments

loanType

Required document checklist

ListPendingReviews

–

Loans under manual review

GetOfficerWorkload

officerName

An officer's assigned loans and workload

SearchLoansByStatus

status

Loans by status

SearchLoansByOfficer

officerName

Loans assigned to an officer

GetLoanAnalytics

–

Portfolio totals and amount statistics

Prerequisites

  • Node.js 22 or later

  • A Microsoft Dataverse environment

  • An Entra ID app registration with a corresponding Dataverse application user (Read access to the loan table)

Getting started

npm install
cp .env.example .env   # then fill in the required values
npm run build
npm start              # HTTP server (dist/http.js)

For local development with reload:

npm run dev:http       # HTTP
npm run dev            # stdio

Configuration

Set these in .env (local) or as environment variables / Azure App settings (hosted).

Required

Variable

Description

TENANT_ID

Entra ID directory (tenant) ID

CLIENT_ID

App registration (client) ID

CLIENT_SECRET

Client secret value

DATAVERSE_URL

e.g. https://yourorg.crm.dynamics.com

Common optional (defaults in parentheses)

Variable

Description

MCP_API_KEY

Shared secret for the HTTP endpoint (x-api-key). Strongly recommended when exposed.

DATAVERSE_LOAN_TABLE

Loan entity set name (cr174_loanapplics)

HTTP_PORT / HTTP_HOST

Listen port/host (PORT or 3000 / 0.0.0.0)

LOG_LEVEL

info

See .env.example for the full list, including the WhatsApp settings below.

Usage

The server is transport-only; a client drives the tools.

  • Claude Desktop (stdio): point an mcpServers entry at node dist/index.js (or npm run start:stdio).

  • Copilot Studio / remote (HTTP): add an MCP tool at https://<host>/mcp with API-key auth (header x-api-key).

GET /healthz returns liveness and WhatsApp status.

WhatsApp (optional)

Lets users query loans over WhatsApp. Enabled only when HUGGINGFACE_API_KEY and the TWILIO_* variables are set.

  1. Set HUGGINGFACE_API_KEY (or another OpenAI-compatible endpoint via LLM_BASE_URL / LLM_MODEL).

  2. Create a Twilio WhatsApp Sandbox; set TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN, TWILIO_WHATSAPP_FROM.

  3. In the sandbox settings, set the inbound webhook to https://<host>/whatsapp (POST).

  4. Set TWILIO_VALIDATE_SIGNATURE=true once the URL is stable.

Deployment

Deployed on Azure App Service. Pushing to main builds and deploys via GitHub Actions (.github/workflows/main_loan-mcp-server.yml). Set all required and secret variables as App settings; Azure runs npm start (the HTTP server) and injects PORT automatically.

Scripts

Script

Description

npm run build

Compile TypeScript to dist/

npm start

Run the HTTP server

npm run start:stdio

Run the stdio server

npm run dev / dev:http

Run from source with reload

npm run typecheck

Type-check without emitting

npm test

Integration test (requires a populated .env)

npm run test:http

Integration test over HTTP

License

MIT

Install Server
F
license - not found
A
quality
B
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

View all tools

Related MCP Servers

  • GoldenGate MCP Server

    elbachir-salik
    F
    license
    -
    quality
    D
    maintenance
    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.
    Last updated
    1

  • Meridian Bank MCP Server

    saivarmadpr
    F
    license
    -
    quality
    B
    maintenance
    A production-grade MCP server for a fictional digital bank, exposing tools for an AI copilot to service customers across the full risk spectrum from read-only lookups to money movement and destructive admin actions, with OAuth 2.1 security and a realistic dataset.
    Last updated
    20

View all related MCP servers

Related MCP Connectors

  • Mini Accountant

    Hosted MCP server for Mini Accountant: invoices, expenses, customers, analytics, tax estimates.

  • classquill-mcp

    Read-only MCP server for ClassQuill, a tutoring-business-management platform.

  • MedPrice AI

    Hosted MCP server exposing US hospital procedure cost data to AI assistants

View all MCP Connectors

Latest Blog Posts

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/Yogeshwara7/loan-mcp-server'

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