Install Jentic One Beta

Connect the AgentMart API to your agent

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

Search the catalog and read one item in full

Buy an item from the owner's balance and list past orders with their receipts

Start a balance top-up and poll its status until it is paid

Claim store credit for an item that failed and review a purchase

Provision and run always-on utilities such as durable queues, webhook inboxes, uptime checks, and scheduled wake-ups

GET STARTED

Start building with AgentMart API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use AgentMart API for, with concrete tasks.

★ Agent Self-Service Purchasing

Let an agent buy what it needs without a human in the checkout. The agent searches the catalog, reads an item in full, and places an order against the prepaid balance its owner funded, then checks the order's receipt and delivery. If an item fails, the agent claims store credit and leaves a review.

Search the catalog, read an item, and place an order from the balance, then check its receipt

Always-On Agent Utilities

Give an agent durable building blocks it would otherwise host itself. From a purchased plan the agent provisions a queue, a webhook inbox, an uptime check, or a scheduled wake-up, then operates it: enqueue and claim messages, read inbox entries, or list check results. These utilities keep running between agent sessions.

Create a queue utility, put messages on it, then claim and acknowledge them

AI Agent Integration via Jentic

An AI agent discovers and calls AgentMart through Jentic. The agent searches by intent, receives the matching operation and its input schema, and places an order or runs a utility while Jentic injects the stored credential. This lets the agent transact from its balance without reading the reference docs or holding secrets.

Search Jentic for 'buy a catalog item', load the operation schema, and place the order with Jentic-injected credentials

Key Endpoints

160 endpoints — the agentmart api lets an ai agent shop a catalog and buy utilities and tested starter kits from a prepaid balance its owner tops up.

METHOD

PATH

DESCRIPTION

GET

/v1/catalog

Search the catalog

GET

/v1/catalog/{slug}

Read one catalog item in full

POST

/v1/orders

Buy an item from the balance

GET

/v1/orders

List the owner's orders

POST

/v1/topups

Start a balance top-up

POST

/v1/reviews

Review a purchase

GET

/v1/catalog

Search the catalog

GET

/v1/catalog/{slug}

Read one catalog item in full

POST

/v1/orders

Buy an item from the balance

GET

/v1/orders

List the owner's orders

POST

/v1/topups

Start a balance top-up

POST

/v1/reviews

Review a purchase

Why Jentic?

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

Setup

Wiring AgentMart by hand means proving a key pair for a passport, choosing between a bearer token and an Ed25519 request signature per operation, and tracking the balance so orders do not fail. Through Jentic you install once, import AgentMart from the API Directory, store the credential once, and your agent calls it.

Permission scoping

AgentMart holds a wide surface, so through Jentic you limit the agent to the operations it needs, such as searching the catalog and placing orders, while leaving passport revocation, account lockdown, and refund operations out of the set.

Credential isolation

Your AgentMart 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 'buy a catalog item' or 'create a queue', and Jentic returns the matching AgentMart operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using AgentMart API through Jentic.

What authentication does the AgentMart API use?

The AgentMart API authenticates read and routine operations with a bearer token tied to your passport, sent in the Authorization header, per its OpenAPI spec. Sensitive actions require an Ed25519 request signature in the Signature header rather than a bearer token, and some public endpoints need no credential. Through Jentic the credential is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent.

Is there an AgentMart MCP server?

You do not need to wire up a separate MCP server to give your agent AgentMart. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls its catalog, order, and utility operations on demand. Operations are discovered as needed, so no extra server's tool definitions load into the agent's context.

Can my agent buy an item from its balance with the AgentMart API?

Yes. Search the catalog, read an item in full, then place an order against the prepaid balance the owner topped up. The order carries a receipt and delivery record, and if the item fails the agent can claim store credit.

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

Yes. Because you run Jentic One yourself, your rules decide which AgentMart operations the agent may call. You can allow catalog search and placing orders while withholding passport revocation, account lockdown, and refund operations, and every call is logged.

What are the rate limits for the AgentMart API?

The OpenAPI spec does not specify request rate limits; spending is bounded instead by the prepaid balance and the per-utility plan limits each item carries. See the AgentMart documentation at https://agentmart.ciphyr.ai for current terms.

How do I buy a catalog item with the AgentMart API through Jentic?

Search Jentic for 'buy a catalog item' to get the matching AgentMart operation and its input schema, then your agent places the order against the balance and reads the receipt. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Ciphyr AgentMart API

AI ReadinessAI-Aware (B+)68/100

See full scorecard

Official vendor OpenAPI document · agent-readyE CommerceStorefrontbearer, apiKey160 EndpointsREST

For Agents

Let an agent search a catalog, place orders from a prepaid balance, and run utilities like queues and uptime checks, across 160 endpoints secured with a bearer token or request signature.

Use for: Search the catalog for a utility I can buy, I need to buy a starter kit from my balance, Get the status of a top-up until it is paid, List my owner's orders with their receipts

Not supported: Does not run its own card payment processing or host your application code. Use for an AI agent to buy utilities and starter kits from a prepaid balance and operate them only.

The AgentMart API lets an AI agent shop a catalog and buy utilities and tested starter kits from a prepaid balance its owner tops up. An agent proves a key pair to get a passport, searches the catalog and reads an item in full, places orders, and reviews purchases, with refunds and store credit for items that fail. Beyond the shop, it provisions and runs always-on utilities such as durable queues, webhook inboxes, uptime checks, scheduled wake-ups, and reminder emails. Money is handled in integer US cents and orders carry receipts and delivery records.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

95%

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).

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.

75%

Response Coverage

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

93%

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: ASignals: 4

70%

Description Coverage

Coverage of descriptions across API elements.

97%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

99%

OperationId Quality

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

58%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: B-Signals: 1

62%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: BSignals: 1

67%

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: C-Signals: 1

51%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the AgentMart API to your agent

Capabilities

Start building with AgentMart API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Ciphyr AgentMart API

Jentic AI Readiness Score

AgentMart 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