Skip to content

Setup & Connection

The Prediko MCP server exposes a curated, task-shaped tool surface for AI agents (e.g. Claude) acting on behalf of a Prediko tenant. It covers inventory planning, purchasing, demand forecasting, and operational insights for e-commerce / DTC brands — the supply-chain loop of forecast demand → identify stock gaps → create purchase orders → track deliveries.

https://mcp.prediko.io/mcp

Point any MCP-capable client at the URL above. OAuth runs on first connect — sign in with your Prediko account and approve the requested scopes.

Claude Code

Terminal window
claude mcp add --transport http prediko https://mcp.prediko.io/mcp

Cursor / VS Code (mcp.json)

{
"mcpServers": {
"prediko": {
"url": "https://mcp.prediko.io/mcp"
}
}
}

Codex (~/.codex/config.toml)

[mcp_servers.prediko]
url = "https://mcp.prediko.io/mcp"

The server authenticates with OAuth 2.1, backed by Auth0. Every tool call resolves the calling user’s tenant from the validated JWT — there is no API-key auth on the MCP surface (that’s the REST API).

  1. Your MCP client runs the OAuth 2.1 authorization-code flow against Prediko’s Auth0 tenant. Sign in with your Prediko account and approve the requested scopes on the consent screen.
  2. The client receives an access token (JWT) and attaches it as a bearer token on every MCP request. Tokens are verified server-side against Auth0’s JWKS (RS256).

Scopes are advertised on the connector’s protected-resource metadata so the consent screen can show what the agent is asking for:

ScopeGrants
read:inventoryAll read / search tools and insights
write:purchase_ordersCreate / update / receive POs, and PO export
write:sku_settingsupdate_sku_settings

MCP access is enabled per tenant. If your tenant has not been enabled, tool calls fail with a “tenant not enabled” error even when your token is valid. Contact hq@prediko.io to request access.

For write tools, the gateway calls Prediko’s backend with a shared service identity but forwards your identity alongside it. Backend audit records therefore attribute each change to you, the real caller — not to a service account. See Write Semantics for the audit_id returned on every write.

The server advertises 9 read tools and 4 write tools. See the full Tool Reference for what each does and its side effects.

ReadsWrites
find_entity, list_entities, get_entitycreate_purchase_order
search_inventory, search_purchase_orders, search_forecastsupdate_purchase_order
get_insights, get_change_history, export_purchase_orderreceive_units, update_sku_settings

Every write tool accepts dry_run=true to preview its effect without persisting — see Write Semantics.