replenishradar
The ReplenishRadar server allows AI agents to access, manage, and act upon inventory, sales, and purchase order data. Key capabilities include:
Inventory & Stock Management
Get stockout risk levels for SKUs, stock-by-location, SKU health summaries, lost sales estimates, and total inventory value breakdowns
List and search inventory items, filtering by vendor or review status
Sales & Demand Analytics
Retrieve demand forecast stats and sales history for SKUs
Identify top-selling and slow-moving SKUs
Purchase Order (PO) Management
List, search, and view POs (including line items, PDFs, and attached documents)
Create and update draft POs, add notes, request human approval, send to suppliers, and cancel POs
Get document upload URLs and record proforma invoice details
Alerts & Replenishment
Retrieve and acknowledge active alerts (filterable by SKU, severity, type, or store)
Get suggested purchase orders and replenishment actions; dismiss, prepare, or execute them (draft or autonomous mode)
Resolve or retry replenishment actions
Suppliers & Sync
List suppliers/vendors and trigger inventory syncs (Shopify or Amazon)
View sync run history, data freshness, store health, setup status, and recent activity
Knowledge & Fit Evaluation
Search the ReplenishRadar knowledge base
Run deterministic ICP and tier fit assessments without org data
Agent Context Store
Get, set, list, and delete bounded key-value memory entries scoped to namespaces (with TTL and size limits)
Permission Tiers
Standard and up: Acknowledge alerts, add notes, request approvals, manage replenishment actions, get upload URLs
Growth and up: Trigger syncs, create/update/send/cancel POs, create manual inventory locations, set stock at manual locations
Provides AI agents with access to live Amazon inventory intelligence, including stockout risk analysis, demand forecasting, and the ability to draft and manage purchase orders.
Provides AI agents with access to live Shopify inventory intelligence, including stockout risk analysis, demand forecasting, and the ability to draft and manage purchase orders.
@replenishradar/mcp-server
Connect AI agents to live ReplenishRadar inventory data. Works with Claude Desktop, OpenClaw, and any MCP-compatible client.
Setup
Get your API key from ReplenishRadar > Settings > API Keys.
Add this server to your MCP client config. In Claude Desktop, open Settings > Developer > Edit Config:
{
"mcpServers": {
"replenishradar": {
"command": "npx",
"args": ["-y", "@replenishradar/mcp-server"],
"env": {
"REPLENISHRADAR_API_KEY": "rr_sk_your_key_here"
}
}
}
}Restart Claude Desktop and ask: "What are my top stockout risks?"
No ReplenishRadar account yet? Use the public agent intake endpoint to request a short-lived, read-only sandbox key before configuring the server:
POST https://api.replenishradar.com/api/public/agent-intakeRelated MCP server: shopico
Available Tools
Read
Standard includes limited read API access. Growth adds diagnosis/status read tools.
Tool | Description |
| Stockout risk levels for SKUs |
| Stock-by-location for an item |
| Demand forecast stats |
| Suggested POs |
| Canonical buyer replenishment actions |
| One replenishment action with event history |
| Active alerts |
| List inventory items |
| Recent sync history |
| List vendors/suppliers |
| List purchase orders |
| Single PO with line items |
| PO PDF info |
| Documents attached to a PO |
| Notes attached to a PO |
| Sales history |
| Top-selling SKUs |
| Slow-moving SKUs |
| Inventory value breakdown |
| SKU-level health summary |
| Estimated lost sales from stockouts |
| Store connection and sync health |
| Freshness status by data dimension |
| Setup milestones and next step |
| Recent alerts, POs, and sync rollup |
| ReplenishRadar product knowledge search |
| Deterministic ICP + tier fit verdict (no org data) |
Basic write (Standard tier and up)
Safe, low-blast-radius writes - no money or stock mutation.
Tool | Description |
| Acknowledge an alert |
| Add a note to a PO |
| Request human approval for a PO |
| Add a note to a replenishment action |
| Dismiss a replenishment action |
| Preview an action and get its current |
| Execute an action. |
| Resolve an action as no-action with a reason; idempotent, stale-state protected |
| Retry a blocked or failed action via the draft execution path; idempotent, stale-state protected |
| Get upload URL for a PO document |
| Record proforma invoice details |
Sensitive write (Growth tier and up)
Money / stock mutation.
Tool | Description |
| Trigger inventory sync |
| Create a draft PO |
| Update a draft PO |
| Send an approved PO |
| Cancel a PO |
| Create a manual inventory location |
| Set stock at a manual location |
PO creation always starts as a draft. rr_send_purchase_order only sends a PO that was already human-approved.
Action execution has two modes. rr_execute_replenishment_action with mode="draft" (the default) creates a draft PO and/or draft transfer for an action's items and never auto-sends to a supplier or commits stock. With mode="autonomous" it additionally sends the PO or commits the transfer, but only when the key has sensitive_write + the operation's tool group + an enabled per-key budget (autonomous_enabled=true) and every guardrail passes; otherwise it leaves a draft and returns an rr_request_approval hint (draft_fallback) or refuses without mutating (hard_refuse). Call rr_prepare_replenishment_action first to get the action's current updated_at, then pass it as expected_updated_at so a stale action is rejected before any write. Pass a stable idempotency_key so a retried call replays the original result instead of double-creating artifacts or double-sending.
Agent context store
A small, org-scoped, auditable key/value memory so an agent can remember bounded workflow state. rr_get_agent_context / rr_list_agent_context are read-capability; rr_set_agent_context / rr_delete_agent_context are basic-write. All four are in the agent_context tool group.
Tool | Description |
| Get one entry by |
| Store a bounded JSON object under |
| List live entries for ONE |
| Delete one entry by |
Rules and limits:
Namespaces are code-owned and per-key allowlisted. A human admin must grant your API key read/write/delete on each namespace in Settings > API Keys. Same-organization access alone is not sufficient.
No secrets, no raw PII. Writes that look like tokens, passwords, private keys, credentials, or raw emails/phones/addresses are rejected.
valuemust be a JSON object (not a scalar or array), capped at 16 KiB serialized.ttl_secondsis optional and capped at 90 days; with no TTL the entry persists while the organization exists.rr_list_agent_contextrequiresnamespaceand never lists across namespaces.scope_refis descriptive metadata only and is not part of uniqueness - encode per-scope entries into thekey(for examplesupplier_rules/sku:ABC123).Sensitive namespaces (for example
sourcing_economics) additionally require the key to hold the sensitive economics read capability + tool group.
Spend budgets (admin-managed, no MCP tool)
Per-API-key spend budgets - per-PO value cap, rolling-24h daily cap, max transfer quantity delta, an autonomous_enabled flag, and vendor / destination / transfer-source (or route-pair) allowlists - constrain what an autonomous key may buy or move. They are managed only by a human admin in Settings > API Keys (a JWT-admin Settings API); there is no MCP tool to read or change a budget, and an API key cannot reach the budget routes, not even for its own caps. Budgets are consumed only by autonomous send/commit, autonomous mode is off by default, and a denied autonomous action receives only a short decision reason - never the cap amounts, the allowlists, or another key's ledger.
Rate Limits
Standard ($99/mo): 10 calls/hour, read + basic-write tools
Growth ($199/mo): 100 calls/hour, read + basic + sensitive read/write + diagnosis/status tools
Scale ($499/mo): 1,000 calls/hour, full read + write capability set
Learn More
Available Tools
16 toolsrr_create_locationB
Create a manual inventory location such as warehouse, 3PL, or inbound location.
Inputs: name (required), type (required), city, state, +4 more.
rr_delete_agent_contextA
Delete one agent context entry by namespace and key. Records actor provenance. The namespace must be granted to this key.
Inputs: key (required), namespace (required).
rr_execute_replenishment_actionA
Execute a replenishment action in draft mode: creates a draft purchase order and/or draft transfer order for the action's items. Idempotent by idempotency_key; rejects with conflict if the action changed since prepare (stale expected_updated_at) or if the same key is reused with a different payload or actor. Never auto-sends to suppliers and never commits stock.
Inputs: action_id (required), idempotency_key (required), expected_updated_at (required).
rr_get_agent_contextA
Get one agent context entry by namespace and key. Expired entries are omitted. The namespace must be granted to this API key by a human admin.
Inputs: key (required), namespace (required).
rr_get_demand_forecastB
Get demand forecast statistics (mu/sigma) for a SKU or item. Returns active forecast windows.
Inputs: sku, item_id, store_id, window_days.
rr_get_document_upload_urlC
Create a document record for a purchase order (invoice, packing slip, etc.). Requires Scale tier.
Inputs: po_id (required), filename (required), description, document_type.
rr_get_purchase_orderA
Get a single purchase order with full details including line items and vendor info.
Inputs: po_id (required).
rr_list_agent_contextA
List live agent context entries for a single namespace. The namespace is required and the limit is bounded (max 200). This tool never lists across namespaces.
Inputs: namespace (required), limit, key_prefix.
rr_list_purchase_ordersB
List purchase orders with filtering by status, vendor, and search. Supports pagination.
Inputs: limit, offset, search, status, +1 more.
rr_list_suppliersA
List all suppliers/vendors for the organization. Optionally include vendor SKU mappings.
Inputs: include_skus.
rr_prepare_replenishment_actionA
Preview a replenishment action and return its current updated_at before executing. Use the returned updated_at as expected_updated_at on execute/resolve/retry.
Inputs: action_id (required).
rr_record_pi_reviewB
Record proforma invoice details on a purchase order (PI number, date, total, terms).
Inputs: po_id (required), pi_date, pi_terms, pi_total, +1 more.
rr_resolve_replenishment_actionA
Resolve a replenishment action as no-action with a reason. Idempotent; requires idempotency_key and expected_updated_at and applies the same stale-state conflict contract as execute.
Inputs: reason (required), action_id (required), idempotency_key (required), expected_updated_at (required).
rr_retry_replenishment_actionA
Retry a blocked or failed replenishment action by re-running the draft execution path. Idempotent; requires idempotency_key and expected_updated_at and applies the same stale-state conflict contract as execute.
Inputs: action_id (required), idempotency_key (required), expected_updated_at (required).
rr_set_agent_contextA
Store a bounded JSON object under a namespace and key. The value must be a JSON object (max 16 KiB), must not contain secrets or raw PII, and ttl_seconds is optional and capped at 90 days. The namespace must be granted to this key.
Inputs: key (required), value (required), namespace (required), scope_ref, +1 more.
rr_set_stock_at_locationC
Set stock quantity for a SKU at a manual location.
Inputs: sku (required), quantity (required), location_id, location_name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Most tools are clearly distinct: forecasting, suppliers, purchase orders, replenishment actions, locations, and agent context each target different resources. The only mild ambiguity is between rr_get_demand_forecast and rr_prepare_replenishment_action, since both relate to replenishment planning, but their descriptions clarify that one returns forecast statistics and the other previews an action.
The rr_ prefix is consistent, and most tools follow a verb_noun pattern (list_suppliers, get_purchase_order, create_location, set_stock_at_location). Minor deviations exist: rr_get_demand_forecast uses a noun phrase rather than a simple verb_noun, and rr_record_pi_review uses an abbreviation, but the overall pattern is predictable.
16 tools is on the higher end but still reasonable for a supply-chain/replenishment domain that spans forecasting, purchase orders, replenishment actions, locations, and agent context. Each tool serves a distinct function, though the agent-context tools (5 tools) could arguably be a separate server.
The core replenishment workflow is well covered: forecast, prepare, execute, resolve, retry, and purchase order read/list. Minor gaps include no update/delete for purchase orders and no supplier creation/update, but these are likely outside the server's purpose. The agent-context CRUD is complete.
Maintenance
Related MCP Connectors
Demand forecasts, reorder points, order quantities and inventory health for Shopify stores.
Inventory, restock planning, and sales analytics for your Amazon FBA business.
Safety-stock & reorder planning, FBA-vs-FBM decision, and inventory health audit for sellers
The AI data platform for commerce: Shopify, Amazon, ads and Klaviyo data with metrics defined once.
Related MCP Servers
- AlicenseAqualityCmaintenanceAI e-commerce operations manager for MCP. Inventory forecasting, pricing optimization, RFM customer segmentation, order anomaly detection, and automated reports for Shopify and WooCommerce.1270 npm1MIT
- FlicenseNot gradedqualityDmaintenanceProvides Shopify demand forecasting, reorder recommendations, and dollar-impact reports as MCP tools.-
- AlicenseNot gradedqualityBmaintenanceEnables natural-language queries of retail sell-through, inventory coverage, out-of-stock risk, and reorder suggestions from POS and warehouse data, with an optional agent that emails reorder proposals.80 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables small shopkeepers to manage inventory conversationally, tracking daily burn rates, predicting stockouts and spoilage, generating supplier-grouped purchase orders, planning reorders under budget constraints, creating near-expiry clearance markdowns, and projecting profit margins.MIT