Install Jentic One Beta

Connect the HaloPSA API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the HaloPSA 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%2Fhalopsa.com%2Fhalopsa" | 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%2Fhalopsa.com%2Fhalopsa" | 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 HaloPSA API.

Open, fetch, and close support tickets in a HaloPSA tenant

Log time and actions against an existing ticket

Create and look up clients and their primary contacts

Track configuration items and assets associated with a client

List active contracts and their billing terms for a client

GET STARTED

Start building with HaloPSA API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use HaloPSA API for, with concrete tasks.

★ MSP Helpdesk Automation

Automate first-line ticket creation by piping monitoring alerts into HaloPSA via POST /tickets and assigning the right agent based on client and asset. The HaloPSA API returns the created ticket with its ID so a downstream alert system can correlate the alert and ticket. This collapses a multi-step manual triage flow into a single API call per alert.

When an SNMP alert fires for client 'Acme Corp', call POST /tickets with summary 'Switch unreachable' and link the affected asset record.

Client Asset and Contract Reconciliation

Reconcile asset inventories and contract entitlements by listing /assets and /contracts for each client and matching them against an external CMDB. Each asset and contract is returned with a clientId so an integration can flag unmanaged devices or expired contracts. This is read-heavy and runs well on a nightly schedule.

List all assets for client ID 142 and contracts for the same client, then flag assets not covered by an active contract.

Billable Time Capture

Capture engineer time against tickets by posting to /actions with the ticketId, agent, duration, and a description, then issuing an invoice via the contract billing flow. HaloPSA tracks billable versus non-billable time per action, so reporting and invoicing stay consistent. Integrators typically pair this with a daily timesheet sync.

Log a 45-minute billable action against ticket 8821 for agent 'Sara' with note 'Replaced failed RAID disk' via POST /actions.

AI Agent Service Desk Copilot

Wire an MSP service desk copilot that reads open tickets via GET /tickets, summarises each customer's queue, and opens follow-ups via POST /tickets. Through Jentic the OAuth Client Credentials are stored centrally and refreshed automatically, so the agent only handles short-lived bearer tokens. The agent cannot run scripts or remote-access endpoints - those are out of scope for this API.

List open tickets for the on-call engineer, summarise priorities, and create a callback ticket for any customer waiting more than 4 hours.

Key Endpoints

35 endpoints — halopsa is a professional services automation platform for managed service providers and it teams, covering ticketing, asset management, contracts, billing, and project tracking.

METHOD

PATH

DESCRIPTION

POST

/auth/token

Obtain an OAuth 2.0 access token

GET

/tickets

List tickets

POST

/tickets

Create a ticket

GET

/tickets/{ticketId}

Get a ticket by ID

POST

/actions

Log an action or time entry against a ticket

GET

/clients

List clients

GET

/assets

List managed assets

GET

/contracts

List service contracts

POST

/auth/token

Obtain an OAuth 2.0 access token

GET

/tickets

List tickets

POST

/tickets

Create a ticket

GET

/tickets/{ticketId}

Get a ticket by ID

POST

/actions

Log an action or time entry against a ticket

GET

/clients

List clients

GET

/assets

List managed assets

GET

/contracts

List service contracts

Why Jentic?

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

Setup

Wiring the HaloPSA API by hand means running its OAuth2 Client Credentials exchange against /auth/token, refreshing the short-lived bearer, pointing calls at your own instance subdomain, and building each ticket, client, and asset request yourself. Through Jentic you install once, import the HaloPSA API from the API Directory, store the client id and secret once, and your agent calls it.

Permission scoping

HaloPSA puts the ticket id in the URL path (/tickets/{ticketId}), so a rule can pin your agent to one ticket: it can read and act on that ticket and nothing else. You choose the operations it may call, so creating tickets or reading clients, assets, and contracts are not included unless you add them.

Credential isolation

Your HaloPSA client id and secret are stored once, encrypted, by your own Jentic One instance, which runs the token exchange and injects the short-lived bearer at execution time. The raw secrets never enter the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'create a support ticket' or 'list clients', and Jentic returns the matching HaloPSA operation with its input schema so the agent calls the right endpoint without crawling the HaloPSA Swagger docs.

FAQs

Specific to using HaloPSA API through Jentic.

What authentication does the HaloPSA API use?

HaloPSA uses OAuth 2.0 Client Credentials. Exchange your client_id and client_secret at POST /auth/token to receive a bearer token, then send Authorization: Bearer <token> on subsequent calls. Tokens are scoped (read:tickets, edit:tickets, read:customers, etc.). Through Jentic, the client_id and client_secret are stored in the encrypted vault and short-lived tokens are minted per call.

Can I create tickets programmatically with the HaloPSA API?

Yes. POST /tickets accepts a JSON body with summary, details, client_id, and priority fields and returns the created ticket with its ticketId. You can then attach actions or time entries via POST /actions referencing the same ticketId.

What are the rate limits for the HaloPSA API?

HaloPSA does not document a public per-second rate limit; tenant-level fair-use throttling applies and HTTP 429 is returned when exceeded. Build clients to back off on 429 and avoid bursting more than a few requests per second per tenant.

How do I open a ticket in HaloPSA through Jentic?

Search Jentic for 'create a halopsa ticket', load the schema for POST /tickets, and execute with summary, client_id, and details. Jentic handles the OAuth client_credentials exchange against /auth/token automatically. Run pip install jentic and use the async client.search, client.load, and client.execute pattern.

Does the HaloPSA API expose remote control or scripting endpoints?

No. This OpenAPI spec covers PSA records - tickets, clients, agents, assets, contracts, invoices, and time. Remote support, scripting, and agent installer flows are not part of the REST surface and require HaloPSA's separate remote tooling.

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

Yes. Jentic One is self-hosted by you, so your own rules decide which HaloPSA operations and credentials the agent may use. You pick the exact endpoints it can call, so listing or creating tickets, reading clients, assets, or contracts, and posting time entries are each off limits unless you add them. Because HaloPSA puts the ticket id in the URL path at /tickets/{ticketId}, a rule can pin the agent to a single ticket, letting it read and act on that one ticket and nothing else.

HaloPSA API

Name: HaloPSA API
Brand: HaloPSA API
Availability: InStock

AI ReadinessAI-Aware (B+)70/100

See full scorecard

Official vendor OpenAPI document · agent-readyCRMCustomer Supportoauth235 EndpointsREST

For Agents

Manage HaloPSA tickets, clients, assets, contracts, and invoices for managed service providers using OAuth 2.0 Client Credentials.

Use for: Open a new HaloPSA ticket for a customer outage, Find all open tickets for client 'Acme Corp', Log a 30-minute time entry against ticket #4421, Retrieve the asset record for a customer laptop

Not supported: Does not handle remote control, scripting, RMM agent installs, or live chat - use for HaloPSA records (tickets, clients, assets, contracts, invoices) only.

HaloPSA is a professional services automation platform for managed service providers and IT teams, covering ticketing, asset management, contracts, billing, and project tracking. The API exposes 35 endpoints for working with tickets, clients, agents, assets, contracts, invoices, and recurring jobs against a per-tenant subdomain. Authentication uses an OAuth 2.0 Client Credentials flow scoped per resource (read:tickets, edit:tickets, read:customers, and so on). The base URL includes a tenant-specific instance variable so each customer reaches their own HaloPSA cloud.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

97%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

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

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

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: D+Signals: 4

34%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

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

62%

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: ASignals: 1

85%

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: A-Signals: 1

71%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the HaloPSA API to your agent

Capabilities

Start building with HaloPSA API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

HaloPSA API

Jentic AI Readiness Score

HaloPSA 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