Install Jentic One Beta

Connect the Spendesk API to your agent

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

Create access token

Retrieve settlement records

Update settlement status

Get a specific payable by ID

Monitor Spendesk API operational status and events

GET STARTED

Start building with Spendesk API

Explore with Jentic One

View OpenAPI Document

Automated Authentication Management

Automate authentication operations by combining multiple Spendesk API endpoints. Agents can retrieve settlement records and then update settlement status in a single workflow.

Call GET /settlements to retrieve settlement records, then verify the result

AI Agent Integration via Jentic

AI agents discover and call Spendesk 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, oauth2 tokens manually.

Search Jentic for 'create access token', load the operation schema, and execute with Jentic-managed credentials

Key Endpoints

42 endpoints — spendesk public api for managing spend data, suppliers, users, purchase orders, analytical fields, webhooks, and accounting exports.

METHOD

PATH

DESCRIPTION

POST

/auth/token

Create access token

GET

/settlements

Retrieve settlement records

PUT

/settlements/state

Update settlement status

GET

/bank-fees

Retrieve bank fee data

POST

/snapshots/payables

Create a payables snapshot

GET

/snapshots/payables

Retrieve a payables snapshot

GET

/payables/{id}

Get a specific payable by ID

GET

/payables/{id}/attachments

Retrieve payable attachments

POST

/auth/token

Create access token

GET

/settlements

Retrieve settlement records

PUT

/settlements/state

Update settlement status

GET

/bank-fees

Retrieve bank fee data

POST

/snapshots/payables

Create a payables snapshot

GET

/snapshots/payables

Retrieve a payables snapshot

GET

/payables/{id}

Get a specific payable by ID

GET

/payables/{id}/attachments

Retrieve payable attachments

Why Jentic?

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

Setup

Wiring Spendesk by hand means running its OAuth2 token flow, carrying the bearer token on every request, and routing across settlements, payables, suppliers, and webhooks yourself. Through Jentic you install once, import the Spendesk API from the API Directory, store the credentials once, and your agent calls it.

Permission scoping

Spendesk puts resource ids in the URL path (/payables/{id}, /suppliers/{id}, /purchase-orders/{id}), so a rule can pin your agent to one payable or supplier: it reads that resource and nothing else. You choose the operations it may call, so ones like deleting a cost center or closing a purchase order are not included unless you add them.

Credential isolation

Your Spendesk credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'get a payable' or 'list suppliers', and Jentic returns the matching Spendesk operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Spendesk API through Jentic.

What authentication does the Spendesk API use?

The Spendesk API uses bearer, oauth2 authentication. 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 access token with the Spendesk API?

Yes. Use the POST /auth/token endpoint. The API returns structured JSON responses that agents can parse and act on directly.

What are the rate limits for the Spendesk 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 access token through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create access token'. Jentic returns the matching Spendesk API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

How many endpoints does the Spendesk API have?

The Spendesk API exposes 42 endpoints covering authentication, spend data, analytical operations.

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

Yes. Because you run Jentic One yourself, your own rules decide which Spendesk operations and credentials the agent may use. Spendesk carries resource ids in the URL path, such as /payables/{id}, /suppliers/{id}, and /purchase-orders/{id}, so a rule can pin the agent to a single payable or supplier and let it read that resource and nothing else. You also choose the operations it may call, so actions like deleting a cost center or closing a purchase order stay out of reach unless you add them.

Spendesk API

Name: Spendesk API
Brand: Spendesk API
Availability: InStock

Official vendor OpenAPI document · agent-readyDeveloper ToolsSource Controlbearer, oauth242 EndpointsREST

For Agents

Programmatically create access token, retrieve settlement records. Covers 42 operations with bearer, oauth2 authentication.

Use for: I need to access token, I want to settlement records, Search for settlement status, Find all bank fee data

Not supported: Does not handle payments, communications, or crm - use for developer tools only.

Spendesk public API for managing spend data, suppliers, users, purchase orders, analytical fields, webhooks, and accounting exports. The API exposes 42 endpoints secured with bearer, oauth2 authentication.

Jentic One on Github View OpenAPI Document

Connect the Spendesk API to your agent

Capabilities

Start building with Spendesk API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Spendesk API