Choose and rank suppliers, size orders and classify spend from delivery and purchase data.
Scored across 2 tools
The two tools perform the same analysis but on different paths (in-server vs. generated script for large sandboxed files), which is a real overlap risk. However, the descriptions draw a clear boundary: file size determines the path, and procurement_get_engine explicitly bakes params into a script without sending supplier data to the server.
Both share the 'procurement_' prefix, but the suffixes follow different conventions: 'get_engine' is verb_noun while 'supplier_selection' is a bare noun phrase. With only two tools, the mix is readable but not a predictable pattern.
Two tools for a domain spanning AHP weighting, robustness, reliability scoring, EOQ/discount analysis, and Kraljic classification is thin and concentrates enormous functionality in one mega-tool. The engine-generator split is justified, but the surface feels undersegmented for the apparent scope.
The main tool covers a broad lifecycle: criteria validation, ranking, robustness, reliability, price-break economics, and an audit decision record with cards. Minor gaps exist—no tool for retrieving/comparing prior decision records or scenario iteration—but core workflows appear covered.
For delivery histories over 1,000 rows or spend files over 500 items that are already in your code sandbox. Returns a complete, runnable numpy-only Python script with the same engine as procurement_supplier_selection; it reads the file(s), runs the full analysis, prints the decision cards and writes procurement_result.json. Pass the small inputs (criteria, pairwise_comparisons, suppliers, price_breaks ...) in params; they are baked into the script. No supplier data reaches this server on this path.
Inputs: params, spend_items_path, delivery_history_path. Returns: notes, script, language, requires, +8 more
Explained, audit-ready supplier selection and buying-quantity decisions in one call. Weights the user's criteria from pairwise importance answers and CHECKS THEM FOR CONTRADICTIONS (AHP consistency ratio; refuses and names the judgement to revisit), ranks suppliers by closeness to the ideal supplier respecting lower-is-better vs higher-is-better criteria (TOPSIS) and tests how robust the winner is to the weights, scores vendor reliability from delivery history (on-time and defect rates with 95% ranges, step-change and steady-drift trend checks, survival of problem-free delivery runs with the chance the next 5 deliveries are fine), works out whether quantity-discount price breaks are worth it (all-units discount EOQ, total annual cost), sorts spend into strategic / leverage / bottleneck / routine (Kraljic), and returns a decision record with an inputs hash and approver. Output starts with plain-language decision cards (CHOOSE, TOO CLOSE, FIX FIRST, STOP USING, ORDER, DO NOT BULK BUY, PROTECT, NEGOTIATE ...). Any subset of inputs works — e.g. only price_breaks for a bulk-discount question. Up to 1,000 delivery rows; larger files: procurement_get_engine.
Inputs: as_of, criteria, currency, item_name, +22 more. Returns: alerts, status, message, metadata, +9 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read-only supply-chain decision support: forecasting, reorder policies, ABC-XYZ, data quality.
Find suppliers ranked for fit across customs records, catalogues and directories
Find the cash trapped in your inventory, then size reorder points, safety stock and EOQ.
Demand forecasts, reorder points, order quantities and inventory health for Shopify stores.
Add one secure layer between your agents and this server.
