Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PTG PMS Connect 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%2Fptg.co.th%2Fptg" | 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%2Fptg.co.th%2Fptg" | 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 PTG PMS Connect API.
Search active employees and separately list employees who are no longer active, filtered by searchText and a dateStart to dateEnd range
Find the subordinates reporting under a position code and fetch one employee by person code
Read the organisation hierarchy: company, divisions, departments, sections, organisation unit types, and work types
List equipment, equipment types, equipment statuses, fuel types, car types, car colors, and account groups
GET STARTED
Retrieve meter logs for one vehicle by carRegister, or the latest meter logs across all cars
Validate an employee or Active Directory login and create a token for a calling system with username, tokenGroup, and systemName
Look up suppliers by vendorID or search text and read the working calendar for a given year and month
Patterns agents use PTG PMS Connect API for, with concrete tasks.
★ Agent lookups across the PTG employee directory
An AI agent answering internal questions can query the PTG PMS Connect API for an employee by person code, search the active directory by name with searchText, and walk the reporting line with the subordinate lookup by position code. Because the division, department, and section lists come from the same API, the agent can place each person in the organisation structure in one session.
Call the subordinate lookup with positionCode P1023, then fetch each returned employee by personCode and group them by department
Fleet meter log monitoring
Operations teams track company vehicle usage from meter logs. The API returns the logs for one vehicle when given its carRegister value, and a paged list of the latest meter logs for all cars, alongside equipment, car type, and fuel type reference lists, so usage reports can be assembled without exporting from the PMS.
Fetch the latest meter logs with page 1 and pageSize 100, then pull the full meter log history for the first carRegister returned
Leaver reconciliation
HR and IT teams need to know who has left so accounts can be closed. The inactive-employee operation lists employees who are not active, filtered by a dateStart and dateEnd window and searchText, which a connected system can compare against its own user list to find accounts that should be removed.
List inactive employees with dateStart 2026-07-01 and dateEnd 2026-09-30 and return their person codes for account review
26 endpoints — the ptg pms connect api exposes ptg's employee directory, organisation structure, and vehicle equipment records to connected systems.
METHOD
PATH
DESCRIPTION
/v1/emp/employees
Get all employees
/v1/emp/GetEmpcodeSubordinate/{positionCode}
Get subordinates by position code
/v1/emp/GetEmployeeByPersonCode/{personCode}
Get an employee by person code
/v1/emp/empnotactive
Get inactive employees
/v1/equip/all
Get all equipment
/v1/equip/meterLogs
Get meter logs by car registration
/v1/master/departments
Get departments
/v1/auth/createtoken
Create a token
/v1/emp/employees
Get all employees
/v1/emp/GetEmpcodeSubordinate/{positionCode}
Get subordinates by position code
/v1/emp/GetEmployeeByPersonCode/{personCode}
Get an employee by person code
/v1/emp/empnotactive
Get inactive employees
/v1/equip/all
Get all equipment
/v1/equip/meterLogs
Get meter logs by car registration
/v1/master/departments
Get departments
/v1/auth/createtoken
Create a token
What agents get from Jentic-routed access to this vendor.
Setup
Wiring PTG PMS Connect by hand means obtaining a bearer JWT, attaching it to the Authorization header, and building the paged POST bodies with page, pageSize, and date ranges that most of its lookups use. Through Jentic you install once, import PTG PMS Connect from the API Directory, store the token once, and your agent calls it.
Permission scoping
Most PTG PMS Connect lookups carry their filters in the request body rather than the URL path, so a rule bounds which operations your agent may call, not which employees or vehicles it reads. You choose the operations it may call, so sensitive ones like Active Directory login validation or token creation are not included unless you add them.
Credential isolation
Your PTG PMS Connect 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 'find an employee's subordinates' or 'get vehicle meter logs', and Jentic returns the matching PTG PMS Connect operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using PTG PMS Connect API through Jentic.
What authentication does the PTG PMS Connect API use?
The PTG PMS Connect API declares HTTP bearer authentication with a JWT sent as Authorization: Bearer {token}, per its OpenAPI spec. The spec also includes a POST /v1/auth/createtoken operation that takes username, tokenGroup, and systemName. Through Jentic the token is stored once and injected at call time, so it never appears in your agent's prompt or logs.
Can I find who reports to a manager with the PTG PMS Connect API?
Yes. GET /v1/emp/GetEmpcodeSubordinate/{positionCode} returns the employees under a position code, and GET /v1/emp/GetEmployeeByPersonCode/{personCode} returns a single employee's record, so an agent can walk a reporting line one level at a time.
What are the rate limits for the PTG PMS Connect API?
The OpenAPI spec does not specify rate limits for the PTG PMS Connect API. Contact PTG support through https://www.ptg.co.th/contact for current limits and access terms.
Which server does the PTG PMS Connect API spec point to?
The spec lists one server, a UAT host at depwn2021.ptg.co.th under the /ptgpmsapi base path. It does not declare a production host, so confirm the right environment with PTG before connecting live systems.
How do I read vehicle meter logs with the PTG PMS Connect API through Jentic?
Search Jentic for 'get vehicle meter logs', which returns POST /v1/equip/meterLogs with its input schema, then send the carRegister value for the vehicle. For every car at once, use POST /v1/equip/latestMeterLogs with page and pageSize. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a PTG PMS Connect MCP server?
You don't need an MCP server to give your agent the PTG PMS Connect API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, discovering operations on demand rather than loading every tool definition into context.
Can I limit what my agent is allowed to do with the PTG PMS Connect API?
Yes. Write a rule that allows only the equipment and meter log operations under /v1/equip, so the agent can report on vehicles but cannot read employee records or call the login validation operations, and every call it makes is logged.
Know of an official OpenAPI document? Contribute it →
For Agents
Look up PTG employees, subordinates by position code, and the division, department, and section hierarchy, and read vehicle equipment, fuel types, and meter logs. Also validates employee and Active Directory logins.
Use for: Find the employees who report to position code P1023, Search for an employee by name in the PTG directory, List all employees who became inactive this quarter, Retrieve the latest meter readings for every company car
Not supported: Does not handle payroll, recruiting, or live vehicle tracking. Use for reading PTG employee, organisation, and equipment records only.
The PTG PMS Connect API exposes PTG's employee directory, organisation structure, and vehicle equipment records to connected systems. It returns active and inactive employees, the subordinates under a position code, and the company, division, department, and section hierarchy, along with equipment lists, fuel and car types, and vehicle meter logs by car registration. It also issues tokens and validates employee and Active Directory logins for the systems that call it. The only server in the spec is a UAT host.
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>