Admin Inventory Management MCP Server
Enables Claude Desktop to manage office inventory through natural language, including adding items, issuing stock, checking availability, and low-stock alerts.
README
π¦ Admin Inventory Management β Remote MCP Server
A production-ready Remote MCP (Model Context Protocol) Server built using FastMCP, enabling Claude Desktop to manage office inventory using natural language.
π Live Endpoint: https://admin-inventory-management-remote-mcp.onrender.com/
π Project Overview
This project implements an AI-powered Office Admin Inventory Management System using the Model Context Protocol (MCP).
It allows Claude Desktop to:
- Add inventory items
- Issue stock
- Check stock availability
- List all items
- Trigger low-stock alerts
All operations are executed via structured tool calls and backed by a persistent database.
π§ Architecture
πΉ Local Architecture
Claude Desktop
β (stdio MCP)
FastMCP Server
β
SQLite Database
πΉ Remote Architecture (Production)
Claude Desktop
β (HTTPS MCP Protocol)
Remote FastMCP Server (Render)
β
SQLite Database
π οΈ Tech Stack
- FastMCP β MCP server implementation
- SQLAlchemy β ORM for database interaction
- SQLite β Persistent storage
- Docker β Containerization
- Render β Cloud deployment
- Claude Desktop β LLM client
βοΈ How It Was Built
1οΈβ£ MCP Tool-Based Server
Inventory operations are exposed as structured tools:
@mcp.tool()
def add_item(name: str, category: str, quantity: int, min_threshold: int):
Each tool:
- Validates inputs
- Executes deterministic business logic
- Updates the database
- Returns structured output
2οΈβ£ Database Layer
Built using SQLAlchemy ORM.
Item Model Fields:
namecategoryquantitymin_threshold
This ensures persistent and reliable inventory tracking.
3οΈβ£ HTTP Transport Mode
Converted from local stdio transport to HTTP transport for remote deployment:
mcp.run(
transport="http",
host="0.0.0.0",
port=port
)
This allows Claude to communicate securely over HTTPS.
4οΈβ£ Dockerized Deployment
Dockerfile used for containerization:
FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 8000
CMD ["python", "server.py"]
Deployed as a Web Service on Render.
π Live Endpoint Behavior
Opening the URL in a browser may show:
Not Found
This is expected behavior.
MCP servers expose protocol endpoints β not web UI routes.
π How to Configure in Claude Desktop
Step 1: Open Claude Settings
Go to:
Settings β Developer β MCP Servers
Step 2: Edit Claude Configuration File
Windows:
%APPDATA%\Claude\claude_desktop_config.json
Mac:
~/Library/Application Support/Claude/claude_desktop_config.json
Step 3: Add Remote MCP Server Configuration
{
"mcpServers": {
"admin-inventory-remote": {
"transport": "http",
"url": "https://admin-inventory-management-remote-mcp.onrender.com"
}
}
}
Step 4: Restart Claude Desktop
Claude will automatically:
- Discover available tools
- Enable natural language inventory management
π§ͺ Example Usage in Claude
You can now say:
- βAdd 200 ball pens in Stationery category with threshold 40.β
- βIssue 30 ball pens.β
- βCheck stock of printer paper.β
- βList all items in inventory.β
Claude will:
- Interpret intent
- Select appropriate MCP tool
- Send structured arguments
- Execute backend logic
- Return updated inventory status
π― Key Design Principles
πΉ Separation of Concerns
- LLM handles reasoning
- MCP handles structured execution
- Database ensures persistence
πΉ Deterministic Backend
The LLM does not directly manipulate the database. All operations pass through validated business logic.
πΉ Secure Protocol Communication
Claude communicates with the server using MCP over HTTPS.
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.