Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Captivated Messaging 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%2Fcaptivated%2Fcaptivated" | shStep 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%2Fcaptivated%2Fcaptivated" | 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.
What an agent can do with Captivated Messaging API.
Send a single SMS to a recipient and retrieve its delivery status by messageId
Submit a bulk send job containing many recipients and poll the resulting jobId
Retrieve per-recipient status from a bulk send job's progress endpoint
Validate a destination phone number before sending to confirm it is reachable
GET STARTED
Drive transactional and marketing SMS workflows from existing CRM and ticketing tools
Patterns agents use Captivated Messaging API for, with concrete tasks.
★ Single Transactional SMS
Workflow tools send order confirmations, OTP codes, and delivery alerts via POST /api/command/v1/messages. Latency matters here, so each call goes one-recipient-at-a-time and polls GET /api/command/v1/messages/{messageId} for delivery confirmation. Volume per call is low but frequency is high across the day.
POST /api/command/v1/messages with the recipient phone number and the message body, then poll GET /api/command/v1/messages/{messageId} to confirm delivery.
Bulk Campaign Send
Marketing campaigns submit a list of recipients to POST /api/command/v1/messages/bulk_create, which queues the send and returns a jobId. The tool polls GET /api/command/v1/jobs/{jobId} for progress and per-recipient outcomes, then writes results back to the CRM.
POST /api/command/v1/messages/bulk_create with the array of recipients and message body, then poll GET /api/command/v1/jobs/{jobId} until status is complete.
Pre-Send Phone Validation
Before charging customers for sends to bad numbers, GET /api/command/v1/phone_number_lookups/{phoneNumber} validates each number's format and reachability. The result either passes the number through to a send queue or quarantines it for manual review.
GET /api/command/v1/phone_number_lookups/+15551234567 and only enqueue numbers that the lookup marks as reachable.
AI Agent SMS Workflows
An agent that handles ticket follow-ups uses Captivated via Jentic to send a personalised SMS once a ticket closes. It searches for the send-message operation, loads the schema, and submits the message - credentials stay encrypted in your Jentic One instance throughout.
Search Jentic for 'send a Captivated SMS', load the createMessage schema, and execute POST /api/command/v1/messages with the recipient and body.
5 endpoints — jentic publishes the only available openapi specification for captivated messaging api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/api/command/v1/messages
Send a single SMS
/api/command/v1/messages/bulk_create
Submit a bulk SMS job
/api/command/v1/messages/{messageId}
Get delivery status for a message
/api/command/v1/jobs/{jobId}
Track a bulk send job
/api/command/v1/phone_number_lookups/{phoneNumber}
Validate a phone number
/api/command/v1/messages
Send a single SMS
/api/command/v1/messages/bulk_create
Submit a bulk SMS job
/api/command/v1/messages/{messageId}
Get delivery status for a message
/api/command/v1/jobs/{jobId}
Track a bulk send job
/api/command/v1/phone_number_lookups/{phoneNumber}
Validate a phone number
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Captivated Messaging API by hand means creating a non-expiring bearer token, sending it in the Authorization header on every call, and polling job status against the api.captivated.works host yourself. Through Jentic you install once, import the Captivated Messaging API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Captivated carries the recipient in the request body, not the URL path, so you scope by operation: limit the agent to the operations it needs, such as sending a message or validating a phone number, and keep bulk create out of the allowed set unless you add it.
Credential isolation
Your Captivated bearer token is stored once, encrypted, by your own Jentic One instance and injected into the Authorization header 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 Captivated SMS' or 'submit a Captivated bulk job', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Captivated Messaging API through Jentic.
Why is there no official OpenAPI spec for Captivated Messaging API?
Captivated does not publish an OpenAPI specification on its developer site. Jentic generates and maintains this spec so that AI agents and developers can call Captivated Messaging 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 Captivated Messaging API use?
Captivated uses bearer token authentication. Tokens are user-created, non-expiring, and revocable from the user profile. Through Jentic the token is stored encrypted in the vault and injected into the Authorization header at execution time.
Can I send a bulk SMS with the Captivated API?
Yes. POST /api/command/v1/messages/bulk_create accepts an array of recipients in one request and returns a jobId. Poll GET /api/command/v1/jobs/{jobId} for the per-recipient delivery status.
How do I check a phone number's deliverability through Jentic?
Search Jentic for 'validate a phone number with Captivated', load the lookupPhoneNumber operation, and execute GET /api/command/v1/phone_number_lookups/{phoneNumber}. The response indicates whether the number is reachable.
What are the rate limits for the Captivated Messaging API?
Captivated does not enumerate rate limits in the OpenAPI spec. Bulk sends are queued asynchronously, so prefer bulk_create over many single calls and back off on 429 responses.
What is the difference between this slug and captivated.works/main?
Both slugs point to the same Captivated platform. captivated.works/main is the canonical vendor-domain slug; captivated/main is an alternate slug some pipelines pin to. New integrations should prefer captivated.works/main.
Can I limit what my agent is allowed to do with the Captivated Messaging API?
Yes. Because Captivated carries the recipient in the request body rather than the URL path, you scope access by operation in your self-hosted Jentic One instance, and your own rules decide which operations the agent may call. You can allow just the operations it needs, such as sending a single message with POST /api/command/v1/messages or validating a number with GET /api/command/v1/phone_number_lookups/{phoneNumber}, while keeping the bulk send POST /api/command/v1/messages/bulk_create out of the allowed set. The bearer token stays with your Jentic One instance and is only used for the operations you permit.
Know of an official OpenAPI document? Contribute it →
For Agents
Send single or bulk SMS messages, retrieve delivery status, track bulk send jobs, and validate phone numbers via the Captivated A2P platform. Mirrors the captivated.works spec under an alternate slug.
Use for: Send a transactional SMS to a customer, Submit a bulk SMS job to thousands of contacts, Get the delivery status of a previously sent message, Track the progress of a Captivated bulk job
Not supported: Does not handle voice calls, email delivery, or in-app push notifications - use for SMS, bulk SMS, and phone number validation only.
Jentic publishes the only available OpenAPI specification for Captivated Messaging API, keeping it validated and agent-ready. Captivated is an A2P messaging platform focused on SMS, and this API exposes endpoints for single sends, bulk send jobs, message status retrieval, bulk job result tracking, and phone number validation. It is the alternate-slug variant of the Captivated platform spec, mirroring the same operations against the same production base URL. Customer engagement teams use it to integrate SMS into existing workflow tools without building against vendor SDKs directly.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
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>