Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the 100ms Video Conferencing 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%2F100ms.live%2F100ms" | 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%2F100ms.live%2F100ms" | 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 100ms Video Conferencing API.
Create video conferencing rooms with recording, region, and size settings
List and filter rooms by template, name, or enabled state
Retrieve a live active room and the peers currently connected to it
Generate room codes for every role or for a single named role
List past sessions and filter them by room or active state
GET STARTED
Update an existing room's recording, webhook, and duration settings
Patterns agents use 100ms Video Conferencing API for, with concrete tasks.
★ Agent-Driven Meeting Provisioning
An AI agent creates a 100ms room on demand, applies recording and region settings, and hands back join codes for each role so participants can enter without manual dashboard steps. Through Jentic the agent discovers the create-room and room-code operations by intent and calls them with a stored management token, keeping room setup fully programmatic.
Create a 100ms room named 'weekly-standup' with recording enabled, then generate room codes for the host and guest roles
On-Demand Class and Webinar Rooms
Education and events platforms create a fresh 100ms room for each scheduled class or webinar, choose a region such as EU or US, cap the session with a maximum duration, and issue per-role join codes for hosts, speakers, and viewers. The room's recording configuration captures the session for later playback, and room size can be raised for large audiences.
Create a room in the EU region with a maximum duration of 3600 seconds and generate a viewer room code
Live Session Monitoring
Operations teams inspect which 100ms rooms are live, list the peers connected to each active room, and filter historical sessions by room to audit attendance and troubleshoot call quality. Peer listings can be narrowed by role or by user to find a specific participant.
Retrieve the active room for a given room id and list its connected peers filtered by the host role
9 endpoints — jentic publishes the only available openapi specification for 100ms video conferencing api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/rooms
Create a new room
/rooms
List rooms
/rooms/{room_id}
Retrieve a specific room
/rooms/{room_id}
Update a room
/active-rooms/{room_id}/peers
List peers in an active room
/sessions
List sessions
/room-codes/room/{room_id}
Create room codes for all roles
/rooms
Create a new room
/rooms
List rooms
/rooms/{room_id}
Retrieve a specific room
/rooms/{room_id}
Update a room
/active-rooms/{room_id}/peers
List peers in an active room
/sessions
List sessions
/room-codes/room/{room_id}
Create room codes for all roles
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the 100ms API by hand means generating a management token from your app access key and secret, setting the bearer header, and handling recording and webhook options yourself. Through Jentic you install once, import 100ms from the API Directory, store the token once, and your agent calls it.
Permission scoping
100ms puts the room id in the URL path (/rooms/{room_id} and /active-rooms/{room_id}), so a rule can pin your agent to one room and the operations you pick. You choose the operations it may call, so destructive ones like room updates are not included unless you add them.
Credential isolation
Your 100ms management token 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 'create a video room' or 'generate a room code', and Jentic returns the matching 100ms 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 100ms Video Conferencing API through Jentic.
Why is there no official OpenAPI spec for 100ms Video Conferencing API?
100ms does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call 100ms Video Conferencing API via structured tooling. It is validated against the live API and kept up to date. To run it on your own infrastructure, install Jentic One from its GitHub repo.
What authentication does the 100ms Video Conferencing API use?
The 100ms Video Conferencing API authenticates with a bearer management token generated from your app access key and secret, passed in the Authorization header per its OpenAPI spec. Through Jentic the token is stored once, encrypted, by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I generate join codes for specific roles with the 100ms Video Conferencing API?
Yes. One operation creates room codes for every role defined on a room, and another creates a code for a single named role, so you can hand a host, a speaker, and a viewer their own join codes for the same room. Each code is tied to the room id in the URL path.
Can I limit what my agent is allowed to do with the 100ms API?
Yes. Write a rule that allows only the room-code and active-room read operations for one room id, so your agent can issue join codes and inspect who is connected to that room and touch nothing else, and every call it makes is logged.
What are the rate limits for the 100ms Video Conferencing API?
The OpenAPI spec does not specify rate limits. Check the 100ms documentation at https://www.100ms.live/docs for current limits before running an agent at high volume against the room and session endpoints.
How do I create a 100ms room through Jentic?
Search Jentic for the intent 'create a 100ms video room', which returns the create-room operation and its input schema; the agent then posts the room name and settings and receives the room id. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a 100ms MCP server?
You don't need an MCP server to give your agent the 100ms API. Jentic connects it directly from the API Directory: import it, store your management token once, and your agent calls the room, session, and room-code operations. Because operations are discovered on demand, no extra tool definitions are loaded into the agent's context.
Know of an official OpenAPI document? Contribute it →
For Agents
Create 100ms video conferencing rooms, generate role-based room codes, and inspect active rooms, their connected peers, and past sessions server-side. Works with a bearer management token.
Use for: Create a video conferencing room for a live class, Generate a room code so a guest can join as a viewer, List the peers currently connected to an active room, Check whether a session is still active for a given room
Not supported: Does not handle in-call media streaming, client-side SDKs, or live transcription. Use for server-side 100ms room, session, and room-code management only.
Jentic publishes the only available OpenAPI specification for 100ms Video Conferencing API, keeping it validated and agent-ready. The 100ms Video Conferencing API manages server-side video and audio rooms, letting you create rooms with recording, region, and size settings, list and retrieve rooms, inspect active rooms and their connected peers, and review past sessions. It generates room codes for every role or for a single named role so participants can join a call, and it caps sessions with a maximum duration while forwarding events to a webhook. The API works with a bearer management token and targets programmatic conferencing rather than a hosted meeting interface.