Inventory Intelligence & Optimizer
Takes a stock list (and sales history if available) and returns order quantities, reorder points, safety stock, overstock, cash tied up in inventory, and a buying list grouped by supplier. Accepts normal business column names (Item Code, Closing Stock, Open PO, Lead Time…) without renaming.
| |
|---|
| Registry name | ai.saifs/inventory-intelligence-optimizer |
| Endpoint | https://inventory-optimizer-mcp.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-inventory-optimizer": {
"type": "http",
"url": "https://inventory-optimizer-mcp.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://inventory-optimizer-mcp.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-inventory-optimizer https://inventory-optimizer-mcp.saifs.ai/mcp
Any other MCP client
Point it at https://inventory-optimizer-mcp.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
| Tool | What it does |
|---|
inventory_optimizer | Scores up to about 200 products and 2,500 sales rows: order quantities, reorder points, overstock, cash exposure and a supplier-grouped purchase queue. |
inventory_optimizer_get_engine | For larger stock books: returns a runnable Python script that does the same analysis locally, so the data never leaves the user's machine. |
Example prompts
- “Here's our stock report. What should we order this week and how much?”
- “Which items are overstocked and how much cash is stuck in them?”
- “Build a purchase list grouped by supplier within a budget of ₹5,00,000.”
Support