Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Rappi Restaurant Integrations 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://jentic.com/install.sh?src=apis&api=%2Fapis%2Frappi.com%2Frappi" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Frappi.com%2Frappi" | 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 Rappi Restaurant Integrations API.
Create or update a menu
List menus
Get menu approval status
Take an order
Access Rappi Restaurant Integrations API developer tools resources via REST API
GET STARTED
Patterns agents use Rappi Restaurant Integrations API for, with concrete tasks.
★ Developer Tools Operations
Use the Rappi Restaurant Integrations API to perform developer tools operations programmatically. The API provides 34 endpoints covering core functionality including create or update a menu, list menus, get menu approval status.
Call POST /menu to create or update a menu
Automated Availability Management
Automate availability operations by combining multiple Rappi Restaurant Integrations API endpoints. Agents can list menus and then get menu approval status in a single workflow.
Call GET /menu to list menus, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Rappi Restaurant Integrations API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle bearer tokens manually.
Search Jentic for 'create or update a menu', load the operation schema, and execute with Jentic-managed credentials
34 endpoints — rappi's public api for restaurant integrations.
METHOD
PATH
DESCRIPTION
/menu
Create or update a menu
/menu
List menus
/menu/approved/{storeId}
Get menu approval status
/menu/rappi/{storeId}
Get latest menu for store
/orders
List new orders
/orders/status/sent
List orders in SENT status
/orders/{orderId}/take/{cookingTime}
Take an order
/orders/{orderId}/reject
Reject an order
/menu
Create or update a menu
/menu
List menus
/menu/approved/{storeId}
Get menu approval status
/menu/rappi/{storeId}
Get latest menu for store
/orders
List new orders
/orders/status/sent
List orders in SENT status
/orders/{orderId}/take/{cookingTime}
Take an order
/orders/{orderId}/reject
Reject an order
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Rappi Restaurant Integrations API by hand means learning its bearer auth and hand-coding requests across its menu and order endpoints. Through Jentic you install once, import the Rappi Restaurant Integrations API from the API Directory, store the bearer token once, and your agent calls it.
Permission scoping
Rappi puts the store and order ids in the URL path (/menu/approved/{storeId}, /orders/{orderId}/take/{cookingTime}), so a rule can pin your agent to one store: it can read menus and orders for that store and nothing else. You choose the operations it may call, so ones like rejecting an order are not included unless you add them.
Credential isolation
Your Rappi bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get pending orders' or 'update a store menu', and Jentic returns the matching Rappi operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Rappi Restaurant Integrations API through Jentic.
What authentication does the Rappi Restaurant Integrations API use?
The Rappi Restaurant Integrations API uses a Bearer token in the Authorization header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I create or update a menu with the Rappi Restaurant Integrations API?
Yes. Use the POST /menu endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Rappi Restaurant Integrations API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I create or update a menu through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create or update a menu'. Jentic returns the matching Rappi Restaurant Integrations API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Rappi Restaurant Integrations API have?
The Rappi Restaurant Integrations API exposes 34 endpoints covering availability, menu, orders operations.
Can I limit what my agent is allowed to do with the Rappi Restaurant Integrations API?
Yes. Because Rappi puts the store and order ids in the URL path (for example /menu/approved/{storeId} and /orders/{orderId}/take/{cookingTime}), a rule in your self-hosted Jentic One can pin the agent to a single store so it only reads menus and orders for that store. You decide which operations the agent may call, so a sensitive action like rejecting an order (PUT /orders/{orderId}/reject) is not available unless you add it. Since Jentic One runs under your own control, your rules and the Rappi bearer token you store there govern exactly which endpoints and credentials the agent can use.
For Agents
Programmatically create or update a menu, list menus. Covers 34 operations with bearer authentication.
Use for: I need to or update a menu, I want to menus, Search for menu approval status, Find all latest menu for store
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
Rappi's public API for restaurant integrations. Allows partners to manage menus, orders, stores, availability, webhooks, and scheduling for their restaurant operations on the Rappi platform. The API exposes 34 endpoints secured with bearer authentication.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>