Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Boxkite Agent 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%2Fgetboxkite.com%2Fgetboxkite" | 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%2Fgetboxkite.com%2Fgetboxkite" | 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 Boxkite Agent API.
Start a read-only export of a Xero organisation's data
List the Xero organisations connected to the account
Poll an export's status and progress until it is ready
Read the manifest describing every file in an export
Read the mapping from each exported file to its Xero object
GET STARTED
Get a short-lived signed URL to download the export ZIP
Patterns agents use Boxkite Agent API for, with concrete tasks.
★ Agent-Driven Xero Export
An AI agent that needs a copy of a user's Xero data can call the Boxkite Agent API through Jentic to start a read-only export, poll it until it is ready, and fetch a signed download URL for the ZIP. The agent runs the export without the developer wiring the bearer auth or the status polling by hand, and because Boxkite requests only read-only scopes the export cannot change the books. Jentic returns the matching operation and its input schema so the agent runs the export inline.
Start an export for a connected Xero organisation, poll it until ready, and fetch the signed download URL
Accounting Data Archive
A firm that wants an off-platform archive of its books can export each connected organisation on a schedule and store the ZIP elsewhere. Boxkite produces the export as a ZIP with a manifest and holds a signed download URL during a retention window, so a workflow can archive a point-in-time copy of the accounting data without modifying anything in Xero.
Export every connected organisation, download each ZIP, and store it in an external archive
File-to-Object Reconciliation
A workflow reconciling documents can use the export's mapping to tie each file to the Xero object it represents or is attached to, such as which invoice a receipt PDF belongs to. Boxkite returns a file-to-object mapping alongside the manifest, so an agent can match exported files to their accounting records without opening each one.
Read an export's mapping and list the invoice each exported receipt file is attached to
7 endpoints — the boxkite agent api produces a read-only export of a user's xero accounting data as a downloadable zip with a manifest and a file-to-object mapping.
METHOD
PATH
DESCRIPTION
/exports
Start a read-only export
/exports
List exports and poll status
/exports/{id}
Get export status and progress
/exports/{id}/manifest
Get the export manifest
/exports/{id}/mapping
Get the file-to-object mapping
/exports/{id}/download
Get a signed download URL for the ZIP
/organisations
List connected Xero organisations
/exports
Start a read-only export
/exports
List exports and poll status
/exports/{id}
Get export status and progress
/exports/{id}/manifest
Get the export manifest
/exports/{id}/mapping
Get the file-to-object mapping
/exports/{id}/download
Get a signed download URL for the ZIP
/organisations
List connected Xero organisations
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Boxkite by hand means handling its bearer API key, completing the one-off Stripe checkout that start-export returns, and polling the export until its signed download URL is ready. Through Jentic you install once, import Boxkite from the API Directory, store the key once, and your agent calls it.
Permission scoping
Every Boxkite operation is read-only, so it cannot modify the books, and Boxkite puts the export id in the URL path so a rule can bound your agent to the export operations you pick. You choose which operations it may call, such as starting, polling, and downloading exports.
Credential isolation
Your Boxkite API key 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 'export a Xero organisation' or 'download an export', and Jentic returns the matching Boxkite operation with its input schema so the agent calls the right endpoint directly.
Alternatives and complements available in the Jentic catalogue.
Specific to using Boxkite Agent API through Jentic.
What authentication does the Boxkite Agent API use?
The Boxkite Agent API authenticates with a bearer API key on every operation, per its OpenAPI spec. Through Jentic the key is stored once, encrypted, by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs.
Is there a Boxkite MCP server?
You don't need an MCP server to give your agent the Boxkite Agent API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent can start and download exports straight away.
Can I limit what my agent is allowed to do with the Boxkite Agent API?
Yes. Every Boxkite operation is read-only, so an export can never modify the books, and Boxkite puts the export id in the URL path so a rule can bound your agent to the export operations you pick. Allow it to list organisations, start and poll exports, and download them, and every call it makes is logged.
Can I export a Xero organisation's data with the Boxkite Agent API?
Yes. The start-export operation begins a read-only export for a connected organisation and returns a checkout URL for the one-off payment, after which an agent polls the export and fetches a signed URL to download the ZIP.
What are the rate limits for the Boxkite Agent API?
The OpenAPI spec does not publish a numeric rate limit; a completed export's download URL stays valid only during a retention window. Check the Boxkite documentation for the current limits on your plan.
How do I export Xero data with the Boxkite Agent API through Jentic?
Search Jentic for an intent like 'export a Xero organisation's data' and it returns the Boxkite export operations with their input schemas, so your agent starts the export, polls it, and downloads the ZIP. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Start a read-only export of a Xero organisation's books, poll it to completion, read its manifest and file-to-object mapping, and fetch a signed URL to the export ZIP. Authenticates with a bearer API key.
Use for: Start an export of a Xero organisation's data, List the Xero organisations I have connected, Check the status of a running export, Download the ZIP for a completed export
Not supported: Does not modify Xero data, manage invoices, or run payroll. Use for read-only export of Xero organisation data only.
The Boxkite Agent API produces a read-only export of a user's Xero accounting data as a downloadable ZIP with a manifest and a file-to-object mapping. An agent lists the connected Xero organisations, starts an export for one of them, and polls it to completion, then reads the manifest describing every file and the mapping that ties each file to its Xero object, such as which invoice a receipt belongs to. A signed download URL serves the ZIP during a retention window. Boxkite requests only read-only Xero scopes, so an export cannot modify the user's books, and starting an export returns a checkout URL for a one-off payment per organisation. Responses are JSON.
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>