Agent-ready OpenAPI document · curated by JenticCommunicationsSms Messagingbasic, apiKey17 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Send SMS, voice, rich content, and surveys, read inbox messages, manage scheduled batches, and subscribe to delivery webhooks via Esendex. Authenticate with HTTP Basic or an Authorization header API key.
Use for: Send an SMS to +447900900123 saying 'your order has shipped', Estimate the cost of sending 5,000 SMS to UK numbers, List inbox messages received in the last 24 hours, Get the conversation thread for phone number +14155550100
Not supported: Does not handle email delivery, push notifications, or video calls - use for SMS, rich-content messaging, surveys, and inbound webhooks only.
Jentic publishes the only available OpenAPI specification for the Esendex API, keeping it validated and agent-ready. Esendex provides SMS, voice, rich-content messaging, surveys, and webhook subscriptions for business communications. The 17 endpoints cover the full message lifecycle: dispatch via /messagedispatcher, list message headers and inbox, read conversations by phone number, manage scheduled batches, send rich content and surveys, and create webhook subscriptions per account. Authentication is dual: HTTP Basic for the historical SMS endpoints and an apiKey Authorization header for newer rich-content and survey routes.
Install Jentic One Beta
Connect the Esendex API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Esendex 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.
1
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%2Fesendex.com%2Fesendex" | sh2
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%2Fesendex.com%2Fesendex" | 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.
Capabilities
What an agent can do with Esendex API.
Dispatch one or many SMS messages in a single call via /messagedispatcher
Estimate the cost of a message before sending with /messages/information
List message headers and read inbox messages received from customers
Pull a conversation thread by phone number for two-way messaging UIs
Schedule message batches and cancel pending schedules before send
Send rich-content messages and check their delivery status
Send surveys and subscribe to delivery and inbound webhooks scoped per account reference
Use Cases
Patterns agents use Esendex API for, with concrete tasks.
★ Two-Way SMS Customer Engagement at Scale
Operations teams running SMS support and notifications need send, read, and conversation-thread endpoints to power agent UIs and automation. Esendex's /messagedispatcher, /inbox/messages, and /conversation/{phonenumber}/messages endpoints provide the full two-way flow without a separate inbound parser, so an agent can read, classify, and reply in the same loop.
Call POST /messagedispatcher with the recipient number and body, then GET /conversation/{phonenumber}/messages to confirm the new outbound entry.
Scheduled SMS Marketing Campaigns
Marketing teams scheduling SMS sends need a batch creation and management surface. Esendex's /messagebatches endpoints let an agent name and schedule batches, list past sends, and cancel a pending schedule before it fires, replacing custom queue plumbing with native scheduling.
Call POST /messagedispatcher with a batch payload and a future send-at timestamp, then PUT /messagebatches/{id} to set a friendly name.
Rich Content and Survey Outreach
Brands using rich messaging or running CSAT surveys via SMS need richer content than 160-character text. Esendex's /send rich-content endpoint and /surveys/{id}/send + /surveys/{id}/report/standard pair handle delivery and reporting in one place, so an agent can run a survey campaign and pull standardised CSAT scores end-to-end.
Call POST /surveys/{id}/send with a contact list, then GET /surveys/{id}/report/standard to retrieve completion and score metrics.
AI Agent SMS Tool via Jentic
An AI customer-service agent can be wired through Jentic to read inbox messages and reply by SMS without a custom integration. The agent searches by intent (for example 'send an SMS'), loads the schema, and executes with HTTP Basic credentials scoped from the vault - useful for one-off support replies or scheduled reminders triggered from a conversation.
Use Jentic search('send an sms message'), load the POST /messagedispatcher operation, and execute it with the recipient and body.
Key Endpoints
17 endpoints — jentic publishes the only available openapi specification for the esendex api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
POST
/messagedispatcher
Send one or many SMS messages
POST
/messages/information
Estimate the cost of a message
GET
/messageheaders
List message headers
GET
/inbox/messages
Get inbound messages
GET
/conversation/{phonenumber}/messages
Get a conversation thread
POST
/send
Send rich-content message
POST
/surveys/{id}/send
Send a survey
POST
/accounts/{accountReference}/subscriptions
Create a webhook subscription
POST
/messagedispatcher
Send one or many SMS messages
POST
/messages/information
Estimate the cost of a message
GET
/messageheaders
List message headers
GET
/inbox/messages
Get inbound messages
GET
/conversation/{phonenumber}/messages
Get a conversation thread
POST
/send
Send rich-content message
POST
/surveys/{id}/send
Send a survey
POST
/accounts/{accountReference}/subscriptions
Create a webhook subscription
Jentic AI Readiness Score
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.
E
Esendex API
- Foundational (C)57/100
87
Foundational Compliance57
Developer Experience & Jentic Compatibility44
AI-Readiness & Agent Experience94
Agent Usability30
Security100
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
87
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
98%
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).
50%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
57
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: C+Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
29%
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.
44
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
23%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
53%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
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.
30
Security
Trust, risk posture, and security compliance.
Grade: FSignals: 1
30%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
100
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A+Signals: 1
100%
Descriptive Richness
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>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Esendex by hand means supporting both its HTTP Basic credentials and its Authorization API key, choosing among its messaging, rich-content, and survey hosts, and building your own retries. Through Jentic you install once, import the Esendex API from the API Directory, store both credentials once, and your agent calls it.
Permission scoping
Esendex sends the message body and recipient in the request body rather than the URL, so scope the agent to the operations it needs, such as POST /messagedispatcher or GET /inbox/messages. You pick that allowed set, so an operation like sending a survey at POST /surveys/{id}/send is only reachable if you include it.
Credential isolation
Your Esendex Basic credentials and Authorization API key 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 'send an sms' or 'read the message inbox', and Jentic returns the matching Esendex operation with its input schema so the agent calls the right endpoint without choosing between the auth flavours.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Esendex API through Jentic.
Why is there no official OpenAPI spec for the Esendex API?
Esendex publishes developer documentation at developers.esendex.com but not a downloadable OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call the Esendex API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Esendex API use?
The Esendex API supports two schemes: HTTP Basic for the legacy SMS endpoints and an apiKey Authorization header for newer rich-content and survey routes. Through Jentic both are stored encrypted in your Jentic One instance and injected at execution time.
Can I send an SMS with the Esendex API?
Yes. POST /messagedispatcher accepts one or many message objects (recipient, body, account reference) and returns delivery batch metadata. Read GET /messageheaders/{id} to track per-message state.
What are the rate limits for the Esendex API?
Esendex applies per-account throughput controls based on your plan but does not encode them in the spec. Submit large sends as batches via /messagedispatcher rather than tight per-message loops, and respect 429 backoff.
How do I send a rich-content message through Jentic?
Search 'send rich content message'. Jentic returns the POST /send operation, you load its schema, and execute with the recipient and content payload. The Authorization API key is injected from the vault.
Can I read a conversation thread by phone number?
Yes. GET /conversation/{phonenumber}/messages returns the chronological message history for that number across both directions, useful for a unified inbox UI.
Does the API support webhook subscriptions for inbound messages?
Yes. POST /accounts/{accountReference}/subscriptions creates a webhook subscription scoped to an account, and DELETE /accounts/{accountReference}/subscriptions/{productId}/{eventId} removes one.
Can I limit what my agent is allowed to do with the Esendex API?
Yes. Because you self-host Jentic One, your own rules decide which Esendex operations and credentials the agent can use, so you grant only the endpoints it needs, such as POST /messagedispatcher to send SMS or GET /inbox/messages to read inbound messages. An operation like sending a survey at POST /surveys/{id}/send or creating a webhook via POST /accounts/{accountReference}/subscriptions is reachable only if you include it in that allowed set. Esendex passes the recipient and message body in the request body rather than the URL, so scoping happens at the operation level you control.
GET STARTED