Install Jentic One Beta

Connect the Lakpura® API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Lakpura® 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%2Flakpura.com%2Flakpura" | sh

Step 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%2Flakpura.com%2Flakpura" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with Lakpura® API.

Search customers by name or phone through the search query parameter and read a customer's name, phone, email, and address

List jobs, optionally filtered by customer_id, and read a job's title, status, scheduled_date, and notes

Move a job to open, in_progress, completed, or cancelled with a single status update

Read the signed-in staff member's notifications with subject, message, and sent_at

GET STARTED

Start building with Lakpura® API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Lakpura® API for, with concrete tasks.

★ Job Status Updates from the Field

Staff handling customer jobs keep their status current without opening the app. The agent finds the customer with the search filter, lists that customer's jobs by customer_id, reads the job's scheduled_date and notes, and moves the job to in_progress or completed with the status update. The status field accepts open, in_progress, completed, or cancelled.

Call GET /customers with search 'Nimal Silva', then GET /jobs with that customer_id, then PATCH /jobs/{id} with status 'completed' for the job scheduled today

Customer Lookup Before a Call

Before contacting a customer, an assistant agent pulls the customer record with phone, email, and address and lists the jobs linked to that customer, so the staff member sees every open job and its notes in one summary.

Call GET /customers/{id} for customer '123', then GET /jobs with customer_id '123' and summarise the open jobs and their notes

Staff Broadcasts and Onboarding

An administrator account can broadcast a notification with a subject and message to every active user, and create new staff accounts because self-registration is disabled. The user count endpoint gives administrators the total number of registered users.

With an admin token, call POST /users/create with email 'new.staff@lakpura.com', password, and full_name 'Kamal Perera', then POST /notifications/send with subject 'Welcome' and a message to all active users

AI Agent Staff Assistant via Jentic

An AI assistant works the Lakpura API through Jentic without holding a staff password or JWT in its context. It searches by intent, receives the job or customer operation with its input schema, and executes with the bearer token injected at run time, so updating a job becomes one step in a larger operations routine.

Search Jentic for 'update a Lakpura job status', load the PATCH /jobs/{id} schema, and execute it with the job id and status 'in_progress'

Key Endpoints

12 endpoints — the lakpura® api backs the lakpura staff mobile app on android and ios, letting signed-in staff look up customers, list the jobs attached to them, and move each job through its open, in_progress, completed, or cancelled status.

METHOD

PATH

DESCRIPTION

POST

/auth/login

GET

/customers

List customers

GET

/customers/{id}

Get a customer

GET

/jobs

List jobs

PATCH

/jobs/{id}

Update a job's status

GET

/notifications

List your notifications

POST

/notifications/send

Broadcast a notification

POST

/auth/login

GET

/customers

List customers

GET

/customers/{id}

Get a customer

GET

/jobs

List jobs

PATCH

/jobs/{id}

Update a job's status

GET

/notifications

List your notifications

POST

/notifications/send

Broadcast a notification

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Lakpura by hand means logging in with a staff email and password, holding a short-lived JWT with no refresh token, and logging in again on every 401. Through Jentic you install once, import Lakpura from the API Directory, store the credential once, and your agent calls it.

Permission scoping

Lakpura puts the job id in the URL path (/jobs/{id}), so a rule can pin your agent to one job and the operations you pick. You choose that set, so admin operations like creating users or broadcasting notifications are not included unless you add them.

Credential isolation

Your Lakpura credential 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 'update a job status' or 'find a customer', and Jentic returns the matching Lakpura operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Lakpura® API through Jentic.

What authentication does the Lakpura® API use?

Per its OpenAPI spec, the Lakpura® API uses the bearerAuth scheme: a JWT sent as Authorization: Bearer with protected requests. You get the token from POST /auth/login with email and password. Tokens are stateless and expire after an hour with no refresh token, so log in again on a 401. The login and register endpoints need no token. Through Jentic the credential is stored encrypted by your own Jentic One instance and injected at execution time.

Can I update a job's status with the Lakpura® API?

Yes. PATCH /jobs/{id} takes a status of open, in_progress, completed, or cancelled. To find the job, list jobs with GET /jobs, optionally filtered by customer_id, or read one with GET /jobs/{id} to see its title, scheduled_date, and notes.

What are the rate limits for the Lakpura® API?

The OpenAPI spec does not specify rate limits. Check https://api.lakpura.com/openapi.yaml for the current definition or ask Lakpura for the limits on your account.

Can I register a new account with the Lakpura® API?

No. Self-registration is disabled and POST /auth/register always returns 403. Accounts are staff accounts, and an administrator creates them with POST /users/create using email, password, and full_name, with is_admin to grant admin rights.

How do I mark a job completed through Jentic with the Lakpura® API?

Search Jentic for 'update a Lakpura job status' and it returns the job update operation with its input schema. Execute PATCH /jobs/{id} with status 'completed', and the token is injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a Lakpura MCP server?

You don't need an MCP server to give your agent the Lakpura® API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Operations are discovered by intent on demand, so no extra tool definitions are loaded into the agent's context.

Can I limit what my agent is allowed to do with the Lakpura® API?

Yes. Allow only the customer and job reads plus PATCH on jobs, and the agent can look up customers and move jobs along while it cannot broadcast notifications or create users. For a narrower task, allow GET and PATCH on one job id only, and every call it makes is logged by your own instance.

Lakpura® API

AI ReadinessFoundational (D)46/100

See full scorecard

Official vendor OpenAPI document · agent-readyE CommerceOrder Managementbearer12 EndpointsREST

For Agents

Look up Lakpura customers and their jobs, update a job's status, read staff notifications, and, with an admin account, create staff users or broadcast a notification.

Use for: Find the customer Nimal Silva and list their jobs, Mark job 38577 as completed, List all jobs for this customer, Check my latest Lakpura notifications

Not supported: Does not handle payments, bookings checkout, product catalogs, or creating new jobs. Use for staff lookups of Lakpura customers and jobs, job status updates, and staff notifications only.

The Lakpura® API backs the Lakpura staff mobile app on Android and iOS, letting signed-in staff look up customers, list the jobs attached to them, and move each job through its open, in_progress, completed, or cancelled status. Staff read their own notifications, while administrators create staff accounts, see the total user count, and broadcast a notification with a subject and message to every active user. Sessions use a JWT bearer token from the login endpoint that expires after an hour with no refresh token.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

85%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B+Signals: 4

30%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

48%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

31%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

52%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: A-Signals: 1

75%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: B-Signals: 1

61%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Lakpura® API to your agent

Capabilities

Start building with Lakpura® API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Lakpura® API

Jentic AI Readiness Score

Lakpura® API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness