io.github.CSOAI-ORG/inventory-management-ai-mcp

Calculate optimal reorder point, safety stock, and economic order quantity using statistical service level targeting. Args: avg_daily_demand: Average units sold per day lead_time_days: Supplier lead time in days safety_stock_days: Buffer days of safety stock service_level: Target service level (0.90, 0.95, 0.97, 0.99, 0.999) demand_std_dev: Standard deviation of daily demand (0 = use safety_stock_days instead) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Forecast future demand from historical sales data with confidence intervals. Args: historical_data: List of historical demand values (e.g. monthly sales) periods_ahead: Number of periods to forecast (1-52) method: Forecasting method (moving_average, exponential_smoothing, linear_trend, seasonal) seasonality_period: Period length for seasonal method (e.g. 12 for monthly data) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Classify SKUs using ABC/XYZ analysis and recommend inventory strategies. Args: skus: List of SKUs as [{"sku": "ABC123", "revenue": 50000, "quantity": 200, "cost": 50, "demand_cv": 0.3}] Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Plan warehouse zone layout optimized for picking efficiency. Args: zones: Warehouse zones as [{"name": "Electronics", "sku_count": 200, "daily_picks": 500, "storage_type": "shelf"}] total_sqft: Total warehouse square footage picking_method: Picking strategy (wave, zone, batch, discrete) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Detect inventory shrinkage by comparing expected vs actual quantities. Flags anomalies and provides category-level analysis. Args: inventory_records: Records as [{"sku": "X", "expected_qty": 100, "actual_qty": 95, "value_per_unit": 25.0, "category": "electronics"}] Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.