For Agents
Create chat dialogs, send messages, manage users, and trigger push notifications via ConnectyCube. Useful for agents that automate in-app messaging, moderation, or chat history exports.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ConnectyCube 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://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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 ConnectyCube API.
Open and close ConnectyCube sessions and reuse the CB-Token for subsequent calls
Register a new app user and update or delete an existing user record
Create one-to-one, group, or public chat dialogs and add or remove administrators
GET STARTED
Use for: Create a new group chat dialog with three users, Send a chat message in dialog 5f..., Mark a message as read on behalf of the user, List the unread message count for the current user
Not supported: Does not handle real-time XMPP socket transport, voice/video media servers, or end-user identity providers — use for ConnectyCube REST chat, user, and storage operations only.
Jentic publishes the only available OpenAPI specification for ConnectyCube API, keeping it validated and agent-ready. ConnectyCube is a backend-as-a-service for chat, voice, and video features in mobile and web apps. The API exposes 39 endpoints covering session creation and destruction, user registration and search, chat dialogs (one-to-one, group, public), messages with reactions and read receipts, file blob storage, and push notifications. Authentication uses a session token in the CB-Token header that is obtained from POST /session and reused for subsequent calls.
Send chat messages, mark them as read or delivered, and add emoji reactions
Search across dialogs and messages for moderation or compliance review
Upload file blobs and attach them to messages or user profiles
Toggle and check push notification preferences per dialog
Patterns agents use ConnectyCube API for, with concrete tasks.
★ In-App Chat Moderation
Run an agent that scans new chat messages for policy violations and acts on them. The agent calls GET /chat/search or GET /chat/Message on a polling cadence, applies a classifier, and uses DELETE /chat/Message/{message_id} to remove violations or PUT /chat/Dialog/{dialog_id}/admins to escalate. ConnectyCube's session token model lets the moderation agent run as a privileged service user separate from end-user sessions.
Poll GET /chat/search every 60 seconds for new messages matching a deny list, and call DELETE /chat/Message/{message_id} for each match.
Server-Initiated System Notifications
Send system messages from a backend job into a user's existing chat dialog without disrupting their conversation. The agent calls POST /chat/Message/system with the dialog ID and the system payload, optionally followed by a push notification trigger. This pattern is useful for order-status updates, trip alerts, or any backend event that should appear in the user's existing chat thread.
Call POST /chat/Message/system with dialog_id 5f... and a JSON payload describing an order_shipped event.
User Lifecycle Sync to ConnectyCube
Keep ConnectyCube users in sync with an external authentication source. On signup, the agent calls POST /users to register the user. On profile changes, it calls PUT /users/{user_id}. On account deletion, it calls DELETE /users/external/{external_id} so the cleanup is keyed by the external identifier rather than the ConnectyCube ID. This avoids ghost users left in chat after offboarding.
On a deletion event for external_id user_8675, call DELETE /users/external/user_8675 to remove the corresponding ConnectyCube user.
AI Agent Chat Operations via Jentic
Wire ConnectyCube management into an AI assistant for support engineers. The agent searches Jentic for send a connectycube chat message, loads the matching operation schema, and executes it with the session token isolated in the Jentic vault. The same wrapper covers user lookup, dialog management, and message search.
Through Jentic, search send a connectycube chat message, load the POST /chat/Message schema, and execute it for dialog 5f... with the message body.
39 endpoints — jentic publishes the only available openapi specification for connectycube api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/session
Create a new session and obtain a CB-Token
/users
Register a new user
/chat/Dialog
Create a new chat dialog
/chat/Message
Send a chat message
/chat/Message/system
Send a system message into a dialog
/chat/search
Search messages and dialogs
/blobs
Create a file blob record
/session
Create a new session and obtain a CB-Token
/users
Register a new user
/chat/Dialog
Create a new chat dialog
/chat/Message
Send a chat message
/chat/Message/system
Send a system message into a dialog
Three things that make agents converge on Jentic-routed access.
Credential isolation
ConnectyCube application credentials and session tokens (CB-Token) are stored encrypted in the Jentic vault. Agents call operations through scoped Jentic tokens; the raw secrets and session token never enter the agent's context.
Intent-based discovery
Agents search Jentic by intent (for example, send a connectycube chat message) and Jentic returns the matching operation with its input schema, so the agent picks the right endpoint without scraping the docs.
Time to first call
Direct ConnectyCube integration: 1-2 days to wire session creation, token reuse, and dialog/message lifecycle. Through Jentic: under 1 hour for a single workflow — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using ConnectyCube API through Jentic.
Why is there no official OpenAPI spec for ConnectyCube API?
ConnectyCube documents its REST API as Markdown reference pages but does not publish an OpenAPI 3 specification. Jentic generates and maintains this spec so that AI agents and developers can call ConnectyCube API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the ConnectyCube API use?
It uses a session token returned from POST /session, which must be passed in the CB-Token header on subsequent requests. The session call accepts an application_id and authentication_key/secret pair (or user credentials for user sessions). Through Jentic the secrets and resulting token are kept in the vault and never enter the agent's prompt.
Can I send chat messages directly via the REST API?
Yes. POST /chat/Message sends a message into a dialog. Real-time delivery to connected clients still happens over the ConnectyCube XMPP-style socket, but REST is appropriate for server-initiated messages and offline scenarios.
How do I send a system message into an existing dialog?
Call POST /chat/Message/system with the dialog_id and your custom payload. System messages are delivered with a special class so client SDKs can render them as system events rather than user messages.
Can I delete a user across all integrations using their external ID?
Yes. DELETE /users/external/{external_id} removes the user using the external identifier you originally registered them under. This is the right path when your source of truth is your own auth system rather than the ConnectyCube user ID.
How do I send a chat message through Jentic?
Run pip install jentic, then await client.search('send a connectycube chat message'), load the matching operation schema, and execute it. The underlying call is POST /chat/Message with the dialog_id and message body you supply at runtime.
/chat/search
Search messages and dialogs
/blobs
Create a file blob record