Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CommPeak SMS Streams 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%2Fcommpeak.com%2Fsms-streams-api" | 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%2Fcommpeak.com%2Fsms-streams-api" | 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 CommPeak SMS Streams API.
Send a single SMS message via POST /simple_send
Send a batch of SMS messages in one POST /simple_send call
Check delivery status for one or more message ids via POST /messages_status
GET STARTED
For Agents
Send single or batched SMS messages and check delivery status on CommPeak SMS Streams with one API key.
Use for: Send a single SMS through CommPeak SMS Streams, Send a batch of SMS messages in one request, Check the delivery status of a sent SMS, Confirm whether yesterday's SMS batch was delivered
Not supported: Does not handle voice calls, dialler campaigns, HLR lookups, or billing - use for sending SMS messages and checking delivery status only.
Jentic publishes the only available OpenAPI specification for CommPeak SMS Streams API, keeping it validated and agent-ready. The SMS Streams service is CommPeak's lightweight SMS-only surface, separate from the broader CommPeak dialler API. It exposes two endpoints: send one or more SMS messages in a single call, and check delivery status for previously sent messages. Intended for developers and QA teams that need a thin send-and-check loop without the dialler, billing, or HLR complexity of the main API.
Use a header-based API key for simple service-to-service auth
Operate as a focused SMS-only sender without dialler dependencies
Patterns agents use CommPeak SMS Streams API for, with concrete tasks.
★ Lightweight OTP Sender
When a backend service needs to send a one-time password and confirm delivery, POST /simple_send with the destination and OTP body, then poll POST /messages_status with the returned message id. The two-endpoint surface keeps the integration small for OTP services that don't need the full CommPeak dialler.
POST to /simple_send with destination +447700900123 and body 'Your code is 482911', then POST /messages_status with the returned id
Bulk Notification Send with Status Reconciliation
Marketing or operational notifications sent in batches can be dispatched in a single POST /simple_send call carrying many messages. Capture each returned id and reconcile delivery via POST /messages_status to identify failures. The thin surface keeps batch sends fast and predictable.
POST a list of 100 messages to /simple_send, capture the ids, then POST those ids to /messages_status and return the count of failed deliveries
QA Smoke Test for SMS Pipelines
QA engineers wiring up an SMS-driven flow can use SMS Streams as the test sender. POST /simple_send fires a known-text message and POST /messages_status confirms it landed, all behind one header key. Useful in CI pipelines that exercise customer SMS journeys before promoting builds.
POST a test message to /simple_send and assert that /messages_status returns delivered within 60 seconds
AI Agent SMS Helper via Jentic
An AI agent connected to Jentic can answer 'send a reminder to this number and let me know if it lands' by calling /simple_send and /messages_status in sequence. Jentic stores the Authorization header key in your Jentic One instance so the agent never sees the raw key.
Use Jentic to search 'send an sms via commpeak sms streams', load /simple_send, and execute with destination and body
2 endpoints — jentic publishes the only available openapi specification for commpeak sms streams api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/simple_send
Send one or many SMS messages
/messages_status
Check delivery status for message ids
/simple_send
Send one or many SMS messages
/messages_status
Check delivery status for message ids
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CommPeak SMS Streams API by hand means learning its API key scheme, hitting its dedicated sendsms host, and polling delivery status yourself. Through Jentic you install once, import the CommPeak SMS Streams API from the API Directory, store the key once, and your agent calls it.
Permission scoping
The CommPeak SMS Streams API sends the recipient and message in the request body, so limit the agent to the operations it needs, such as sending a message or checking its delivery status. You choose the operations it may call, so you can allow status checks while leaving message sending out unless you add it.
Credential isolation
Your CommPeak SMS Streams 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 an SMS message' or 'check message delivery status', and Jentic returns the matching CommPeak SMS Streams 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 CommPeak SMS Streams API through Jentic.
Why is there no official OpenAPI spec for CommPeak SMS Streams API?
CommPeak does not publish an OpenAPI specification for SMS Streams. Jentic generates and maintains this spec so AI agents and developers can call SMS Streams 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 CommPeak SMS Streams API use?
SMS Streams uses an API key passed in the Authorization header. The key is created in the CommPeak portal at my.commpeak.com under SMS Streams. Through Jentic, the key is stored encrypted in your Jentic One instance and never enters the agent's context.
Can I send a batch of SMS messages in one request?
Yes. POST /simple_send accepts a list of messages in a single body, returning an id for each one. This is the recommended approach for marketing or notification batches over the per-message round trip.
How do I check delivery status for a sent SMS?
POST /messages_status with one or more message ids returned from /simple_send. The response contains the per-id delivery state, suitable for reconciling failures and triggering retries.
What are the rate limits for CommPeak SMS Streams?
CommPeak does not document a public rate limit for SMS Streams. In practice batched /simple_send calls scale better than tight per-message loops; expect 429 responses at extreme volume and back off.
How do I send an SMS through Jentic?
Search Jentic for 'send an sms via commpeak sms streams', load the schema for POST /simple_send, and execute with destination and body. The Jentic Python SDK pattern is await client.search(...), await client.load(...), await client.execute(...).
Can I limit what my agent is allowed to do with the CommPeak SMS Streams API?
Yes. Because Jentic One is self-hosted, you decide which operations the agent may call, so you can allow only checking delivery status via POST /messages_status while withholding message sending via POST /simple_send until you choose to add it. Your own rules govern which operations and stored credentials the agent can use, and the CommPeak API key stays in your instance rather than the agent's context. This lets you keep the agent scoped to a read-only status check, or grant sending only when a workflow genuinely needs it.