Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Nimbus MCP Server Look up the user account for sarah.chen@example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Standalone Model Context Protocol (MCP) HTTP server for the Nimbus Furniture platform.
Built with FastMCP and integrated directly with MongoDB Atlas (pure cloud database operations, no local file fallbacks). Exposes live tools to query products, place and manage orders, and retrieve customer account profiles.
Tool | Category | Description |
| Orders | Place a new furniture order into MongoDB Atlas (updates inventory, calculates total, generates tracking) |
| Orders | Retrieve order tracking, delivery estimate, item breakdown, and status by order ID |
| Orders | Retrieve full order history for a customer by email |
| Orders | Cancel an order and automatically restore stock to the product catalog |
| Products | Browse furniture catalog with category and keyword search filters |
| Products | Get full specs, dimensions, materials, stock count, and price for a product |
| Accounts | Look up customer account details, membership plan, and order history count |
| Accounts | Retrieve plan details (Free vs. Premium) and account status/suspensions |
Related MCP server: Ticket Support MCP Server
The server operates against the nimbus_db database on MongoDB Atlas:
products Collection (30 Fake Furniture Items)Contains 30 high-detail furniture records across Chairs, Desks, Sofas, Tables, Storage, Beds, Lighting, and Outdoor. Includes the requested items and schemas:
{
"product_id": "PROD-001",
"product": "chair",
"price": "200rs",
"price_num": 200,
"category": "Chairs",
"description": "Versatile lightweight minimalist stacking chair, ideal for dining or home study.",
"material": "Molded Polymer & Powder-Coated Steel Legs",
"color": "Matte White",
"dimensions": "32H x 18W x 18D inches",
"stock": 50,
"in_stock": true,
"rating": 4.5,
"reviews_count": 89,
"warranty": "1-Year Warranty"
}orders CollectionTracks all customer orders placed through the MCP server (simplified mock schema):
{
"_id": {
"$oid": "6adb6cba92bd13bd47018b6f"
},
"order_id": "ORD-20260801-7102",
"customer_email": "sarah.chen@example.com",
"customer_name": "Sarah Chen",
"items": [
{
"product_id": "PROD-002",
"product": "Nimbus Ergonomic Task Chair",
"price": "4500rs",
"quantity": 1
}
],
"total_amount": "4500rs",
"total_price_num": 4500,
"shipping_address": "742 Evergreen Terrace, Springfield"
}pip install -r requirements.txtMONGODB_URI="mongodb+srv://<user>:<password>@cluster0.v3dfdhj.mongodb.net/?appName=Cluster0"
MONGODB_DB_NAME="nimbus_db"
MCP_SERVER_PORT=8001
MCP_SERVER_HOST="0.0.0.0"python seed_db.pypython server.pyServer runs streamable HTTP on http://127.0.0.1:8001/mcp.
This server cannot be deployed
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
Search people and companies, enrich profiles, and find email and phone over MCP.
Pocket Agent (aipocketagent.com) MCP server — read tools for personas, apps, and product info.
