Install Jentic One Beta

Connect the MailJunky API to your agent

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

Send a transactional email with reply_to, tags, metadata, and a category

Send up to 100 emails in a single batch request

Import up to 1,000 contacts per batch and filter contacts by email, tag, or status

Update a contact's properties, tags, or status, such as marking it unsubscribed

Track a user event such as purchase_completed with properties, session_id, and browser context

GET STARTED

Start building with MailJunky API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use MailJunky API for, with concrete tasks.

★ AI agent sending transactional email through Jentic

An order-handling agent needs to email a confirmation the moment a purchase lands. Through Jentic it searches for 'send a transactional email', loads the MailJunky send operation with its input schema, and posts from, to, subject, and html with a category of 'orders'. The live API key is injected at call time, so the agent never holds it.

Call POST /emails/send with from 'orders@yourdomain.com', to 'customer@example.com', subject 'Order confirmed', html, and category 'orders'

Event-driven lifecycle email

A product team wants email to follow what users actually do. MailJunky tracks named events such as purchase_completed or page_viewed for a user, with custom properties, a session_id, and browser context, and its contacts carry tags and properties for segmentation. Event statistics then show which events are firing most.

Call POST /events/track with event 'purchase_completed', user 'jane@example.com', and properties holding the plan name, then GET /events/stats

Contact import and cleanup

Moving an existing list into MailJunky means importing in bulk and keeping status accurate. The batch import accepts 1 to 1,000 contacts per call with names, phone, properties, and tags, contacts can be listed by tag or status, and a contact's status can be updated when someone unsubscribes.

Call POST /contacts/batch with a contacts array of up to 1000 records, then GET /contacts with tag 'customer' and limit 100

Key Endpoints

13 endpoints — the mailjunky api sends transactional email, tracks user events, and keeps a contact list that email workflows can act on.

METHOD

PATH

DESCRIPTION

POST

/emails/send

Send an email

POST

/emails/batch

Send batch emails

POST

/contacts

Create or update a contact

GET

/contacts

List contacts

POST

/contacts/batch

Batch import contacts

POST

/events/track

Track an event

GET

/stats

Get email statistics

POST

/emails/send

Send an email

POST

/emails/batch

Send batch emails

POST

/contacts

Create or update a contact

GET

/contacts

List contacts

POST

/contacts/batch

Batch import contacts

POST

/events/track

Track an event

GET

/stats

Get email statistics

Why Jentic?

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

Setup

Wiring MailJunky by hand means choosing between bearer and X-API-Key auth, keeping live and public keys apart, and honouring Retry-After when rate limited. Through Jentic you install once, import MailJunky from the API Directory, store the key once, and your agent calls it.

Permission scoping

MailJunky puts the contact id in the URL path (/contacts/{id}), so a rule can pin your agent to one contact, while sends and events carry their targets in the request body, so rules there bound which operations it may call. You choose the operations it may call, so ones like batch sends or contact deletion are not included unless you add them.

Credential isolation

Your MailJunky 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 'send a transactional email' or 'track a user event', and Jentic returns the matching MailJunky operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using MailJunky API through Jentic.

What authentication does the MailJunky API use?

MailJunky declares an API key sent as a bearer token in the Authorization header, with the X-API-Key header as an alternative, per its OpenAPI spec. Live keys start with mj_live_, while public mj_pub_ keys are restricted to event tracking. GET /health needs no key. Through Jentic the key is stored by your own instance and attached at call time.

Can I send emails in bulk with the MailJunky API?

Yes. POST /emails/batch takes an emails array of 1 to 100 messages, each with its own from, to, and subject, so one request can send a set of reminders or notifications.

What are the rate limits for the MailJunky API?

The OpenAPI spec does not state a numeric limit, but every response carries X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers, plus Retry-After when you are limited. Check https://mailjunky.ai for plan limits.

Is there a MailJunky MCP server?

You don't need an MCP server to give your agent MailJunky. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the send, contact, and event operations on demand without loading another server's tool definitions into its context.

How do I track an event through Jentic?

Search Jentic for 'track a user event', load the POST /events/track operation, and run it with the event name, the user, and any properties. To run it on your own infrastructure, install Jentic One from its GitHub repo.

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

Yes. For example, a rule that allows POST /events/track and GET /stats lets an analytics agent record events and read email statistics while it cannot send email or delete contacts. Jentic logs each call the agent makes.

MailJunky API

AI ReadinessAI-Aware (B-)63/100

See full scorecard

Official vendor OpenAPI document · agent-readyCommunicationsEmail Deliveryhttp (bearer), apiKey (X-API-Key header)13 EndpointsREST

For Agents

Send transactional email singly or in batches of 100, track user events, and keep tagged contacts with MailJunky, then read email and event statistics.

Use for: I need to send an order confirmation email, Send a batch of reminder emails to this week's trial users, Find all contacts tagged as customers, Track a purchase_completed event for this user

Not supported: Does not send SMS, push notifications, or design marketing campaigns. Use for transactional email, contacts, and event tracking only.

The MailJunky API sends transactional email, tracks user events, and keeps a contact list that email workflows can act on. A send takes from, to, subject, and html or text, with reply_to, tags, metadata, and a category, and a batch call sends up to 100 emails at once. Contacts carry first_name, last_name, phone, custom properties, tags, and a status, and can be imported up to 1,000 per batch or filtered by email, tag, and status. Events such as purchase_completed are tracked with properties, a session_id, and browser context, and statistics summarise email and event activity over ranges such as 7d or 30d.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: BSignals: 4

91%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

75%

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.

48%

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: D+Signals: 4

38%

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.

54%

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: CSignals: 1

55%

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

79%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the MailJunky API to your agent

Capabilities

Start building with MailJunky API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

MailJunky API

Jentic AI Readiness Score

MailJunky 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