For Agents
Query and insert restaurant POS data including menu items, orders, payments, and ingredient inventory across 9 data tables.
Use for: I need to query today's orders from the POS system, Retrieve all menu items in a specific category, I want to insert a new order into the POS, List all payments for a specific order
Not supported: Does not handle online ordering, customer loyalty programs, or staff scheduling — use for POS data query and insert only.
Lavu POS API provides programmatic access to restaurant point-of-sale data including menu groups, menu categories, menu items, orders, order contents, order payments, ingredients, and ingredient usage. The API uses form-encoded POST requests authenticated with a dataname, key, and token combination, and returns data in XML format. It supports querying existing records with filtering and pagination, as well as inserting new records into POS tables.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Lavu POS API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Lavu POS API.
Query menu groups, categories, and items for restaurant catalog management
Retrieve order records with optional column-based and date-range filtering
Insert new records into POS tables for order and inventory updates
Access payment data linked to specific orders for reconciliation
Track ingredient usage to monitor stock levels and cost of goods
Patterns agents use Lavu POS API for, with concrete tasks.
★ Daily Sales Reporting
Query the orders and order_payments tables to generate daily sales summaries for restaurant management. The API supports date-range filtering via value_min and value_max parameters, allowing retrieval of all transactions within a specific time window. Results include order contents and payment breakdowns for accurate revenue reporting.
Query the orders table for all records with value_min set to 2026-06-01 and value_max set to 2026-06-15 to retrieve this period's transactions
Menu Catalog Synchronization
Retrieve menu groups, categories, and items from the POS to synchronize with online ordering platforms or digital menu boards. The API provides the complete menu hierarchy, enabling automated updates when items or pricing change in the POS system.
Query the menu_items table to retrieve all current menu items and their associated pricing data
Inventory and Cost Tracking
Access the ingredients and ingredient_usage tables to monitor stock levels, calculate cost of goods sold, and identify items that need reordering. The API returns usage records that can be correlated with orders to track per-dish ingredient consumption.
Query the ingredient_usage table filtered by a specific date range to calculate total ingredient consumption for the week
AI Agent POS Data Access via Jentic
AI agents use Jentic to discover Lavu POS operations by intent, such as 'query restaurant orders' or 'get menu items'. Jentic returns the operation schema with the required dataname, key, token, and table parameters, so agents can pull POS data without managing XML response parsing or credential handling manually.
Search Jentic for 'query restaurant orders', load the queryData operation schema, and execute a request for orders from the current date
2 endpoints — lavu pos api provides programmatic access to restaurant point-of-sale data including menu groups, menu categories, menu items, orders, order contents, order payments, ingredients, and ingredient usage.
METHOD
PATH
DESCRIPTION
/cp/reqserv
Query records from POS data tables with filtering
/v2/reqserv/
Insert new records into POS data tables
/cp/reqserv
Query records from POS data tables with filtering
/v2/reqserv/
Insert new records into POS data tables
Three things that make agents converge on Jentic-routed access.
Credential isolation
Lavu's dataname, key, and token credentials are stored encrypted in the Jentic vault. Agents receive scoped access so that raw POS credentials never appear in agent context or logs.
Intent-based discovery
Agents search by intent (e.g., 'query restaurant orders' or 'get menu items') and Jentic returns the matching Lavu operation with its required parameters and table options, so the agent can call the right endpoint without parsing XML documentation.
Time to first call
Direct Lavu integration: 2-3 days for XML response parsing, credential management, and table-specific query construction. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Stripe API
Payment processing for online transactions outside the POS
Use Stripe alongside Lavu when you need to process online payments or subscriptions that are separate from in-restaurant POS transactions.
Specific to using Lavu POS API through Jentic.
What authentication does the Lavu POS API use?
The Lavu POS API uses a three-part credential system: dataname (account identifier), key (API key), and token (API token). These are passed as POST body parameters with each request. Through Jentic, all three credentials are stored encrypted in the vault and injected automatically into requests.
Can I query orders by date range with the Lavu POS API?
Yes. The query endpoint accepts value_min and value_max parameters in date-time format, allowing you to filter records within a specific time window. Combine these with the column parameter to specify which date field to filter on, such as order creation time.
What data tables are available in the Lavu POS API?
The API provides access to 9 tables: menu_groups, menu_categories, menu_items, tables, orders, order_contents, order_payments, ingredients, and ingredient_usage. Each table is accessed through the same query endpoint by specifying the table parameter.
What are the rate limits for the Lavu POS API?
Rate limit details are not published in the Lavu POS API specification. The API uses a limit parameter for pagination, and responses are in XML format. Contact Lavu support for account-specific rate limit information.
How do I query restaurant orders through the Lavu POS API with Jentic?
Install the SDK with pip install jentic, then search for 'query restaurant orders'. Jentic returns the queryData operation schema requiring dataname, key, token, and table fields. Set table to 'orders' and optionally add date filters, then execute the call to receive order records.
What format does the Lavu POS API use for requests and responses?
Requests use application/x-www-form-urlencoded format for query operations. The insert endpoint also uses form encoding but includes an XML-formatted contents field for the record data. All responses are returned in XML format, not JSON.
GET STARTED