Content
<p align="center">
<img src="images/banner.png" alt="Sezzle Merchant Local MCP Server" width="1000"/>
</p>
---
<h3 align="center">Unofficial Sezzle Agentic Commerce Local MCP Server</h3>
---
A comprehensive Model Context Protocol (MCP) server for Sezzle Buy Now Pay Later services. This server provides tools for product discovery, affordability analysis, offer comparison, checkout session creation, and order tracking through Sezzle's sandbox environment.
## Features
This MCP server provides access to all major agentic commerce workflows:
### 🛍️ Product Discovery
* search_products - Search products from merchant catalog data
* compare_offers - Compare multiple matching products and installment options
### 💳 Affordability Analysis
* check_affordability - Calculate estimated installment payments
* payment_breakdown - View payment schedule information
### 🛒 Checkout Sessions
* create_session - Create Sezzle checkout sessions
* generate_checkout_url - Generate shopper checkout URLs
### 📦 Order Management
* track_order - Retrieve order status and tracking information
### 🧪 Sandbox Support
* Real Sezzle Sandbox API integration
* Offline mock session mode
* Mock merchant catalog data for demos
---
# Prerequisites
### Sezzle Sandbox Account
You need a Sezzle sandbox merchant account.
### Sandbox API Credentials
Generate sandbox API credentials from the Sezzle Sandbox Dashboard.
Required credentials:
* SEZZLE_PUBLIC_KEY
* SEZZLE_PRIVATE_KEY
---
# Configuration
The server requires the following environment variables:
```env
SEZZLE_ENV=sandbox
SEZZLE_PUBLIC_KEY=your_public_key
SEZZLE_PRIVATE_KEY=your_private_key
SEZZLE_MOCK_SESSIONS=false
```
For offline demonstrations:
```env
SEZZLE_MOCK_SESSIONS=true
```
---
# Installation
```powershell
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -e ".[dev]"
```
Create environment file:
```powershell
Copy-Item .env.example .env
```
Update credentials inside `.env`.
---
# Running the Server
```powershell
python -m sezzle_agentic_commerce.server
```
---
# Available Tools
## search_products
Search products from the merchant catalog.
Example:
```python
search_products({
query: "wireless headphones",
max_price_cents: 20000
})
```
Returns:
* Product name
* Merchant
* Product price
* BNPL eligibility
---
## compare_offers
Compare multiple products matching the search criteria.
Example:
```python
compare_offers({
product_name: "wireless headphones",
max_price_cents: 20000
})
```
Returns:
* Product comparison
* Installment comparison
* Best-value recommendation
---
## check_affordability
Estimate installment payments for a product purchase.
Example:
```python
check_affordability({
product_price_cents: 19999
})
```
Returns:
* Total purchase amount
* Installment amount
* Estimated payment schedule
---
## create_session
Create a Sezzle checkout session.
Example:
```python
create_session({
items: [
{
name: "Wireless Headphones",
quantity: 1,
price_cents: 19999
}
]
})
```
Returns:
* Session UUID
* Checkout URL
---
## track_order
Retrieve order information.
Example:
```python
track_order({
order_uuid: "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
})
```
Returns:
* Order status
* Order UUID
* Payment details
---
# Claude Desktop Configuration
Copy the example configuration into Claude Desktop:
Typical Windows path:
```text
%APPDATA%\Claude\claude_desktop_config.json
```
Example:
```json
{
"mcpServers": {
"sezzle-agentic-commerce": {
"command": "python",
"args": [
"-m",
"sezzle_agentic_commerce.server"
]
}
}
}
```
Restart Claude Desktop after updating the configuration.
---
# Architecture
```text
Claude Desktop
│
▼
MCP Protocol
│
▼
Sezzle MCP Server
│
┌─────┴───────────┐
▼ ▼
Mock Catalog Sezzle Sandbox API
│
▼
Checkout Session
```
---
# Project Structure
```text
sezzle-agentic-commerce/
│
├── sezzle_agentic_commerce/
│ ├── server.py
│ ├── tools/
│ │ ├── search_products.py
│ │ ├── compare_offers.py
│ │ ├── check_affordability.py
│ │ ├── create_session.py
│ │ └── track_order.py
│ │
│ ├── clients/
│ │ └── sezzle_client.py
│ │
│ └── data/
│ └── mock_products.json
│
├── docs/
│ ├── architecture.png
│ ├── claude-demo.png
│ ├── mcp-inspector.png
│ └── demo-video.mp4
│
├── tests/
├── .env.example
├── README.md
└── pyproject.toml
```
---
# Demo Workflow
Paste the following prompt into Claude Desktop:
```text
Find me wireless headphones under $200 that I can split into 4 payments. Compare the offers, pick the best one, check affordability, then create a Sezzle checkout session.
```
Expected tool flow:
```text
1. search_products()
2. compare_offers()
3. check_affordability()
4. create_session()
5. return checkout_url
```
---
# Sezzle API Integration
The server integrates with the following Sezzle sandbox endpoints:
### Authentication
```http
POST /v2/authentication
```
### Create Checkout Session
```http
POST /v2/session
```
### Retrieve Order
```http
GET /v2/order/{order_uuid}
```
---
# Testing
```powershell
pytest
```
---
# Screenshots
### Architecture Diagram
<p align="center">
<img src="images/Architecture.png" alt="Architecture Diagram" width="1000"/>
</p>
### Claude Desktop Demo
https://github.com/user-attachments/assets/9689d847-b82d-4ba6-a7fa-e2b5c6f11f35
---
# Error Handling
The server handles various error scenarios:
* Authentication Errors
* Missing Credentials
* Invalid Product Requests
* Session Creation Failures
* Order Lookup Failures
* Sandbox API Errors
All errors return descriptive messages to help identify and resolve issues.
---
# Support and Documentation
* Sezzle Developer Documentation
* Sezzle Sandbox Environment
* Model Context Protocol (MCP) Documentation
---
# License
This project is licensed under the MIT License.
MCP Config
Below is the configuration for this MCP Server. You can copy it directly to Cursor or other MCP clients.
mcp.json
Connection Info
You Might Also Like
Vibe-Trading
Vibe-Trading: Your Personal Trading Agent
ai-berkshire
Berkshire in the AI Era: A Value Investment Research Framework Based on...
hexstrike-ai
HexStrike AI is an AI-powered MCP cybersecurity automation platform with 150+ tools.
valuecell
Valuecell is a Python project for efficient data management.
tradingview-mcp
AI-assisted TradingView chart analysis — connect Claude Code to your...
tradingview-mcp
TradingView MCP Server offers real-time market analysis for crypto and stocks.