Install Jentic One Beta

Connect the Lettr API to your agent

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

Send a transactional email to up to 50 recipients from html, text, or a template_slug with substitution_data, with an Idempotency-Key for safe retries

Schedule an email for a set scheduled_at time and cancel it by transmission id before it sends

Filter email events by type such as delivery, bounce, spam_complaint, open, or click, and by recipient and date range

Add and verify a sending domain, then subscribe a webhook to message events such as message.delivery and message.bounce

GET STARTED

Start building with Lettr API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Lettr API for, with concrete tasks.

★ Agent-sent transactional email through Jentic

An AI agent handling customer requests can send a templated email with the right merge data and then check its delivery events to confirm it arrived. Through Jentic the agent finds the send operation by intent and the bearer key is injected at execution time, and a rule can allow sending and event reads while leaving domain deletion and campaign sends out of reach.

Call POST /emails with from 'support@example.com', to ['jane@example.com'], template_slug 'order-confirmation', and substitution_data containing the order number, then call GET /emails/events with recipients 'jane@example.com' and events 'delivery,bounce'

Reliable transactional sends

Receipts, password resets, and alerts must arrive once and only once. Lettr sends from html or text or a stored template, tags messages and attaches metadata for later lookup, and honours an Idempotency-Key so a retried request returns the original result instead of sending again, with open and click tracking toggled per message.

Call POST /emails with Idempotency-Key 'reset-8841', from 'no-reply@example.com', to ['user@example.com'], subject 'Reset your password', and html containing the reset link

Deliverability monitoring

Bounces and spam complaints need attention before they damage sender reputation. The Lettr events operation filters by event type, recipient, date range, transmission, and bounce class, and webhooks push events such as message.delivery and message.bounce to your endpoint with basic or OAuth authentication.

Call GET /emails/events with events 'bounce,spam_complaint' for the last day and list the affected recipients

Newsletter audiences and campaigns

Lettr also covers marketing email. Contacts can be added in bulk with properties, attached to lists and subscription topics, and grouped into condition-based segments, and a campaign built from html content or a template can be sent at once or scheduled with scheduled_at, with engagement events available per campaign.

Call POST /audience/contacts with email 'new.subscriber@example.com' and the newsletter list_id, then POST /campaigns/{campaignId}/schedule with scheduled_at '2026-11-09T09:00:00Z'

Key Endpoints

71 endpoints — the lettr api sends transactional email with tracking, attachments, and personalization, either from raw html and text or from a stored template_slug filled with substitution_data.

METHOD

PATH

DESCRIPTION

POST

/emails

Send an email

POST

/emails/scheduled

Schedule an email

GET

/emails/events

List email events

GET

/emails/{requestId}

Get email detail

POST

/domains/{domain}/verify

Verify a sending domain

POST

/webhooks

Create a webhook

POST

/audience/contacts

Create a contact

POST

/campaigns/{campaignId}/send

Send a campaign

POST

/emails

Send an email

POST

/emails/scheduled

Schedule an email

GET

/emails/events

List email events

GET

/emails/{requestId}

Get email detail

POST

/domains/{domain}/verify

Verify a sending domain

POST

/webhooks

Create a webhook

POST

/audience/contacts

Create a contact

POST

/campaigns/{campaignId}/send

Send a campaign

Why Jentic?

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

Setup

Wiring Lettr by hand means managing a bearer key, setting an Idempotency-Key on retries, verifying sending domains, and choosing between html, text, and template_slug content on each send. Through Jentic you install once, import Lettr from the API Directory, store the key once, and your agent calls it.

Permission scoping

Lettr carries recipients and content in the request body, so for sends, rules bound which operations your agent may call, not who it emails. Templates, campaigns, domains, and audience lists carry their ids in the URL path (/templates/{slug}, /campaigns/{campaignId}/send), so those operations can be pinned to one template, campaign, or list. You choose the operations it may call, so destructive ones like deleting a domain or sending a campaign are not included unless you add them.

Credential isolation

Your Lettr 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 'check if an email bounced', and Jentic returns the matching Lettr operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Lettr API through Jentic.

Is there a Lettr MCP server?

You don't need an MCP server to give your agent the Lettr API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls it. Operations are discovered on demand, so your agent's context carries no tool definitions it will not use.

What authentication does the Lettr API use?

Per its OpenAPI spec, the Lettr API uses HTTP bearer authentication with your Lettr API key, and GET /auth/check confirms a key is valid. The health check is declared open. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's context.

Can I retry a Lettr send without sending the email twice?

Yes. Send an Idempotency-Key header with POST /emails. Repeating the same payload with the same key returns the original result without another delivery, while a conflicting payload or a transmission still in progress returns 409.

What are the rate limits for the Lettr API?

The OpenAPI spec does not specify rate limits, though it notes Lettr checks your sending quota before each send. Check https://docs.lettr.com for current limits.

How do I send a templated email with Lettr through Jentic?

Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import the Lettr API from the directory, and store your API key. Your agent then searches for 'send a transactional email' and Jentic returns POST /emails, which requires from and to and accepts a template_slug with substitution_data. To run it on your own infrastructure, install Jentic One from its GitHub repo.

How do I find out whether a Lettr email bounced?

Call GET /emails/events with events set to bounce and recipients set to the address, optionally narrowed by a from and to date range and by bounce_classes. For push delivery, create a webhook with POST /webhooks subscribed to events such as message.bounce.

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

Yes. For a support assistant, write a rule that allows only POST /emails and GET /emails/events: the agent can send transactional emails and check their delivery, but cannot send or schedule campaigns, delete domains, or edit your audience, and every call it makes is logged.

Lettr API

AI ReadinessAI-Aware (B+)70/100

See full scorecard

Official vendor OpenAPI document · agent-readyCommunicationsEmail Deliverybearer71 EndpointsREST

For Agents

Send and schedule transactional emails from HTML or templates, track delivery, bounce, open, and click events, and manage sending domains, templates, audience contacts, and campaigns in Lettr.

Use for: I need to send a password reset email to a user, Send the order confirmation template to this customer with their order details, Schedule a reminder email for tomorrow at 9am, Check whether my email to jane@example.com was delivered or bounced

Not supported: Does not handle SMS, push notifications, inbound email parsing, or inbox hosting. Use for sending and tracking transactional and campaign email only.

The Lettr API sends transactional email with tracking, attachments, and personalization, either from raw html and text or from a stored template_slug filled with substitution_data. A send takes up to 50 recipients plus cc and bcc, and accepts an Idempotency-Key header so retries never deliver the same message twice; messages can also be scheduled for a later time and cancelled before they go out. Delivery is observable through sent-email lists and an event stream covering delivery, bounce, open, click, and unsubscribe events, and the same API manages sending domains, webhooks, templates, audience contacts, lists, topics, segments, and marketing campaigns.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: B-Signals: 4

86%

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).

60%

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: A-Signals: 4

35%

Example Density

How richly the API is illustrated with examples.

99%

Example Validity

Percentage of examples that conform to their schemas.

74%

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: B-Signals: 4

66%

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.

77%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

91%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

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: ASignals: 1

81%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Lettr API to your agent

Capabilities

Start building with Lettr API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Lettr API

Jentic AI Readiness Score

Lettr 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