Sendblue API
✓ Official Vendor SpecCommunicationsEmail DeliveryapiKey9 EndpointsREST
For Agents
Programmatically send message, send group message. Covers 9 operations with apiKey authentication.
Use for: I need to send message, I want to send group message, Search for messages, Find all evaluate messaging service
Not supported: Does not handle payments, crm, or developer tools - use for communications only.
Sendblue iMessage, SMS, and RCS messaging API. The API exposes 9 endpoints secured with apiKey authentication.
Install Jentic One Beta
Connect the Sendblue API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Sendblue 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%2Fsendblue.co%2Fsendblue" | 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%2Fsendblue.co%2Fsendblue" | 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 Sendblue API.
Send message
Get messages
Evaluate messaging service
Create contact
List contacts
Use Cases
Patterns agents use Sendblue API for, with concrete tasks.
★ Communications Operations
Use the Sendblue API to perform communications operations programmatically. The API provides 9 endpoints covering core functionality including send message, send group message, get messages.
Call POST /send-message to send message
Automated Contacts Management
Automate contacts operations by combining multiple Sendblue API endpoints. Agents can send group message and then get messages in a single workflow.
Call POST /send-group-message to send group message, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Sendblue API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'send message', load the operation schema, and execute with Jentic-managed credentials
Key Endpoints
9 endpoints — sendblue imessage, sms, and rcs messaging api.
METHOD
PATH
DESCRIPTION
POST
/send-message
Send message
POST
/send-group-message
Send group message
GET
/accounts/messages
Get messages
GET
/evaluate-service
Evaluate messaging service
POST
/contacts
Create contact
GET
/contacts
List contacts
GET
/contacts/{id}
Get contact
PUT
/contacts/{id}
Update contact
POST
/send-message
Send message
POST
/send-group-message
Send group message
GET
/accounts/messages
Get messages
GET
/evaluate-service
Evaluate messaging service
POST
/contacts
Create contact
GET
/contacts
List contacts
GET
/contacts/{id}
Get contact
PUT
/contacts/{id}
Update contact
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Sendblue API by hand means learning its sb-api-key-id header auth, calling api.sendblue.co, and handling message delivery status yourself. Through Jentic you install once, import the Sendblue API from the API Directory, store the key once, and your agent calls it.
Permission scoping
Sendblue puts the contact id in the URL path (/contacts/{id}) while messages are sent by request body, so scoping stays operations-only: limit the agent to the operations it needs, such as sending a message or reading a contact. You choose the operations it may call, so nothing you do not add is reachable.
Credential isolation
Your Sendblue 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 message' or 'look up a contact', and Jentic returns the matching Sendblue API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Sendblue API through Jentic.
What authentication does the Sendblue API use?
The Sendblue API uses an API key passed in the `sb-api-key-id` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I send message with the Sendblue API?
Yes. Use the POST /send-message endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Sendblue API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I send message through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'send message'. Jentic returns the matching Sendblue API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Sendblue API have?
The Sendblue API exposes 9 endpoints covering contacts, messages, service operations.
Can I limit what my agent is allowed to do with the Sendblue API?
Yes. Because you run Jentic One yourself, your own rules decide which Sendblue operations and credentials the agent may use, so scoping is operations-based. You can grant only the endpoints the agent needs, such as POST /send-message to send a message or GET /contacts/{id} to read a single contact, while withholding actions like POST /contacts or PUT /contacts/{id}. Anything you do not add stays unreachable, so an agent cannot create or update contacts or send group messages unless you allow those operations.
GET STARTED