Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Vonage Video API (formerly OpenTok/TokBox), 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%2Fdeveloper.vonage.com%2Fvonage" | 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%2Fdeveloper.vonage.com%2Fvonage" | 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 Vonage Video API (formerly OpenTok/TokBox) API.
Create video sessions and send signals to a session or a single connection
List and inspect connections and streams, and mute individual streams or a whole session
Record sessions as archives with custom layouts, storage, and stop control
Run live broadcasts and control their layout and streams
GET STARTED
Dial SIP endpoints into a session, send DTMF, and add live captions
Manage projects, their secrets, and render and audio-connector jobs
Patterns agents use Vonage Video API (formerly OpenTok/TokBox) API for, with concrete tasks.
★ Agent-Driven Video Session Orchestration
An AI agent sets up a video call by creating a session, then manages it in flight: muting a disruptive stream, sending a signal to a connection, and starting an archive to record the call. Because every control is an API call, an assistant can run a moderated session without a human in the console.
Create a session, start an archive recording, then mute a named stream when asked and stop the archive at the end
Session Recording and Storage
Record video sessions as archives, apply a custom layout, and route the output to configured storage. A content team can capture every session, list past archives, and fetch a specific archive by id for later processing.
Start an archive for a session with a custom layout, then list the project's archives and fetch the new one by id
Live Broadcast and SIP
Stream a session to a live audience and bring phone participants in over SIP. The broadcast endpoints start, stop, and lay out the stream, while the dial endpoint connects a SIP endpoint and DTMF carries keypad input into the session.
Start a live broadcast for a session, dial a SIP endpoint into it, and stop the broadcast when the session ends
40 endpoints — the vonage video api, formerly opentok, powers real-time video sessions and everything around them.
METHOD
PATH
DESCRIPTION
/session/create
Create a video session
/v2/project/{apiKey}/session/{sessionId}/signal
Send a signal to a session
/v2/project/{apiKey}/session/{sessionId}/connection
List connections in a session
/v2/project/{apiKey}/archive
Start an archive recording
/v2/project/{apiKey}/archive/{archiveId}
Fetch an archive by id
/v2/project/{apiKey}/broadcast
Start a live broadcast
/v2/project/{apiKey}/dial
Dial a SIP endpoint into a session
/v2/project/{apiKey}/render
Start an experience render job
/session/create
Create a video session
/v2/project/{apiKey}/session/{sessionId}/signal
Send a signal to a session
/v2/project/{apiKey}/session/{sessionId}/connection
List connections in a session
/v2/project/{apiKey}/archive
Start an archive recording
/v2/project/{apiKey}/archive/{archiveId}
Fetch an archive by id
/v2/project/{apiKey}/broadcast
Start a live broadcast
/v2/project/{apiKey}/dial
Dial a SIP endpoint into a session
/v2/project/{apiKey}/render
What agents get from Jentic-routed access to this vendor.
Setup
By hand you provision project credentials, build the X-OPENTOK-AUTH token, learn the session, archive, and broadcast models, and wire your own polling for recordings before a call runs. Through Jentic you connect once from the API Directory and your agent calls the operations by intent.
Permission scoping
You grant your agent only the operations it needs, such as creating sessions and recording archives while withholding project secret management. The project key and session id travel in the URL path, so a rule can bind the agent to a single project's operations.
Credential isolation
Your Video credential is stored encrypted on your own Jentic One instance and injected into the X-OPENTOK-AUTH header at execution time, never placed in the agent's prompt, logs, or context. You rotate or revoke it in one place.
Intent-based discovery
Agents search Jentic by intent such as 'create a video session' or 'start an archive', and Jentic returns the matching Vonage Video operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Vonage Video API (formerly OpenTok/TokBox) API through Jentic.
What authentication does the Vonage Video API use?
The spec declares an apiKey scheme that sends a token in the X-OPENTOK-AUTH header, so every request carries that credential. Through Jentic, your own Jentic One instance stores it encrypted and attaches it to each call rather than exposing it to the agent.
Can I record a video session with the Vonage Video API?
Yes. You start an archive for a session, optionally apply a custom layout, and route the output to configured storage, then stop the archive when the session ends. You can list a project's archives and fetch any one by its id.
What are the rate limits for the Vonage Video API?
The OpenAPI spec does not state rate limits. Check the official Vonage Video documentation at https://developer.vonage.com/en/video/ for current limits before scaling up sessions and recordings.
How do I run Vonage Video through Jentic?
Add the Vonage Video API from the Jentic API Directory and connect your credential once. Your agent then searches by intent such as 'create a video session' and calls the matching operation. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I restrict which Vonage Video operations my agent is allowed to call?
Yes. You grant your agent only the operations it needs, such as creating sessions and recording archives while withholding project secret management. The project key and session id sit in the URL path, so a rule can pin the agent to a specific project's operations, and every call is logged.
Is there a Vonage Video API MCP server?
You don't need an MCP server to use the Vonage Video API with your agent. Jentic connects it directly from the API Directory: import it, connect your credential once, and your agent can create and manage sessions without another server loading tool definitions into its context.
For Agents
Create and manage Vonage Video (OpenTok) sessions: signal and mute participants, record sessions as archives, run live broadcasts, dial SIP, add captions, and manage projects. Covers real-time video from session creation to recording and streaming.
Use for: Create a new video session, Start recording a session as an archive, I want to broadcast a session live, Mute every stream in a session
Not supported: Does not handle standalone SMS, voice-call billing, or phone-number provisioning. Use for Vonage Video sessions, archives, broadcasts, and related media only.
The Vonage Video API, formerly OpenTok, powers real-time video sessions and everything around them. You create sessions, send signals, inspect connections and streams, and mute streams or whole sessions. You record sessions as archives with custom layouts and storage, run live broadcasts, dial SIP endpoints into a session, add live captions, and start render and audio-connector jobs. Account endpoints manage projects and their secrets, so an integration can provision and run video end to end.
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.
Start an experience render job
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>