Procurement & Supplier Selection

Procurement & Supplier Selection

Explained, audit-ready supplier choice and buying-quantity decisions from delivery, spend and supplier scores. Weights suppliers with AHP, ranks them with TOPSIS, scores on-time / defect reliability, sizes lots with quantity-discount EOQ, and maps the book into Kraljic spend quadrants. Public-tender mode treats the ranking as supporting evidence only.

Registry name	ai.saifs/procurement-and-supplier-selection
Endpoint	https://procurement-and-supply-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-procurement-supplier-selection": {
      "type": "http",
      "url": "https://procurement-and-supply-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://procurement-and-supply-mcp.saifs.ai/mcp

Claude Code

claude mcp add --transport http saifs-procurement-supplier-selection https://procurement-and-supply-mcp.saifs.ai/mcp

Any other MCP client

Point it at https://procurement-and-supply-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.

Tools

Tool	What it does
procurement_supplier_selection	For up to 1,000 delivery rows, 500 spend items and 60 suppliers: AHP weights, TOPSIS ranking, vendor reliability, EOQ order sizing, Kraljic spend map and a decision record (FOLLOW TENDER RULES, STOP USING, ORDER, NEGOTIATE…).
procurement_get_engine	For larger GRN / spend files: returns a runnable numpy-only script that runs the same engine locally, so the data never leaves the user's machine.

Example prompts

• “Here are last year’s GRNs and spend. Who should we keep, and who should we stop using?”
• “We have three quotes and on-time history. Rank the suppliers and say if the scores are too close to award.”
• “What lot size should we buy given these quantity-discount slabs?”

Support

• Website: https://saifs.ai
• Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
• Privacy: https://saifs.ai/privacy_policy