MCP Servers

razorpay-recon-mcp

MCP server for daily payment reconciliation between Razorpay and Odoo, with WhatsApp alerts for anomalies.

README

Razorpay Reconciliation MCP Server

Daily payment reconciliation: Razorpay payments → Odoo orders → WhatsApp alerts.

Architecture

Razorpay MCP Server (remote) ──┐
                               ├── Razorpay Recon MCP ──→ Odoo (JSON-RPC)
Razorpay REST API (settlements) ┘       │                → WhatsApp (Convertway)
                                        │
                                        └── 8 Tools + Daily Cron (8 AM)

Setup

1. Razorpay API Key

Login to Razorpay Dashboard → Account & Settings → API Keys
Generate Key ID + Key Secret
Encode: echo "key_id:key_secret" | base64
Set RAZORPAY_AUTH_HEADER=Basic <output> in .env

2. Configure Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "razorpay-recon": {
      "command": "node",
      "args": ["dist/main.js"],
      "cwd": "E:\\Razorpay MCP\\razorpay-recon"
    }
  }
}

3. Environment

Copy .env.example to .env and fill in:

Variable	Required	Source
`RAZORPAY_AUTH_HEADER`	Yes	Base64(key:secret)
`ODOO_*`	Yes	Odoo credentials
`CONVERTWAY_*`	For alerts	Convertway WhatsApp
`FINANCE_TEAM_PHONE`	For alerts	WhatsApp number

4. Run

# Development (HTTP)
npm run dev

# Production (HTTP)
npm run build && npm start

# Backtest (read-only, no Odoo writes)
npm run backtest 30

Tools

Tool	Description
`get_payments`	Fetch payments for a date range
`get_refunds`	Fetch refunds for a date range
`get_settlements`	Fetch settlements for a date range
`reconcile_orders`	Match Razorpay payments to Odoo orders
`get_payout_status`	Fetch payout details
`run_daily_reconciliation`	Full 8 AM pipeline
`run_anomaly_detection`	Detect anomalies
`run_backtest`	Backtest over N days

Anomaly Alerts

Condition	Alert
Failed payment > ₹5,000	WhatsApp → finance team
Unmatched settlement	WhatsApp → finance team
Refund volume spike > 1.5× 7-day avg	WhatsApp → finance team

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured