Install Jentic One Beta

Connect the Mosaic AI API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Mosaic AI 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%2Fmosaic.so%2Fmosaic" | sh

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%2Fmosaic.so%2Fmosaic" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 Mosaic AI API.

Run a Mosaic video editing agent on video_inputs, uploaded video_ids, or video_urls, with an optional callback_url

Track a run's status and per-node progress, then resume or cancel it

Upload video, audio, and image files through signed upload URLs and finalize them for use in runs

Trigger an agent automatically from new uploads on watched YouTube channels

GET STARTED

Start building with Mosaic AI API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Mosaic AI API for, with concrete tasks.

★ AI content agent that edits and publishes clips

A content agent can turn a long recording into short clips and post them without a developer wiring Mosaic's upload, run, and publish steps by hand. Through Jentic the agent searches for 'run a Mosaic video agent', loads the run operation with its input schema, and passes the video URL. Your own Jentic One instance attaches the API key at call time, and the agent polls the run, then posts the result to the connected accounts.

Call POST /agent/{agent_id}/run with video_urls containing the recording link, poll GET /agent_run/{run_id} until it completes, then call POST /social/post with the output in media_urls and platforms tiktok and youtube

Editing every new upload from a YouTube channel

Creators who publish long-form video on YouTube can have Mosaic process each new upload automatically. Adding YouTube channel listeners to an agent's triggers starts a run whenever the channel publishes, and the agent's run history can be filtered by status and date range to review what was produced.

Call POST /agent/{agent_id}/triggers/add_youtube_channels with youtube_channels set to the channel ID, then list GET /agent/{agent_id}/runs with status completed to review the outputs

Uploading source media for a run

Local files reach Mosaic through a two-step upload: request a signed upload URL for a video, audio, or image file, upload the file to it, and finalize it with the returned ID. The finalized video_id can then be passed to an agent run.

Call POST /uploads/video/get_upload_url, upload the file to the returned URL, call POST /uploads/video/finalize_upload with the video_id, then run the agent with video_ids containing it

Tracking how published clips perform

After clips go out, a social team wants engagement numbers and audience reactions in one place. Mosaic lists posts by status, platform, or social_connection_id, and returns analytics and comments for each post on a connected account. Queued posts can be rescheduled with a new schedule_date or deleted before they publish.

Call GET /social/posts with platform linkedin, then GET /social/post/{post_id}/analytics for each post with its social_connection_id, and report the top performer

Key Endpoints

56 endpoints — the mosaic ai api builds and runs ai video editing workflows, called agents, made of node types such as video inputs, ai avatar, video generation, audio generation, and image generation tiles.

METHOD

PATH

DESCRIPTION

POST

/agent/{agent_id}/run

Run an agent

GET

/agent_run/{run_id}

Get agent run status

POST

/agent/create

Create an agent

POST

/uploads/video/get_upload_url

Get video upload URL

POST

/agent/{agent_id}/triggers/add_youtube_channels

Add YouTube channel listeners

POST

/social/post

Create social post

GET

/social/post/{post_id}/analytics

Get social post analytics

POST

/agent/{agent_id}/run

Run an agent

GET

/agent_run/{run_id}

Get agent run status

POST

/agent/create

Create an agent

POST

/uploads/video/get_upload_url

Get video upload URL

POST

/agent/{agent_id}/triggers/add_youtube_channels

Add YouTube channel listeners

POST

/social/post

Create social post

GET

/social/post/{post_id}/analytics

Get social post analytics

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Mosaic by hand means choosing bearer or X-API-Key auth, chaining the signed upload and finalize steps before a run, and handling run polling or a callback. Through Jentic you install once, import Mosaic from the API Directory, store the key once, and your agent calls it.

Permission scoping

Mosaic puts the agent id in the URL path, as in /agent/{agent_id}/run, so a rule can hold your agent to one editing workflow and the operations you pick. You choose the operations it may call, so destructive or public ones like deleting an agent or publishing a social post are not included unless you add them.

Credential isolation

Your Mosaic 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 'run a video editing agent' or 'schedule a social post', and Jentic returns the matching Mosaic operation with its input schema, including video_inputs, callback_url, and platforms.

FAQs

Specific to using Mosaic AI API through Jentic.

What authentication does the Mosaic AI API use?

Per its OpenAPI spec, most Mosaic AI API operations accept either a bearer API key in the Authorization header or the same key in the X-API-Key header. The shared-stores operations declare bearer authentication only, and GET /social/connect/{connect_token}, the link an end user opens to connect a social account, needs no key. Through Jentic the key is stored by your own Jentic One instance and attached at call time.

Can I get Mosaic agent run status updates without polling?

Yes. POST /agent/{agent_id}/run accepts an optional callback_url, a webhook URL that receives status updates for the run. You can also poll GET /agent_run/{run_id} for status and GET /agent_run/{run_id}/nodes for per-node progress.

What are the rate limits for the Mosaic AI API?

The OpenAPI spec does not specify rate limits. Check the Mosaic documentation at https://docs.mosaic.so for current limits.

Is there a Mosaic MCP server?

You don't need an MCP server to give your agent Mosaic. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent runs video agents and publishes posts on demand without another server's tool definitions in its context.

Can I limit what my agent is allowed to do with the Mosaic AI API?

Yes. Write a rule that allows only POST /agent/{agent_id}/run and GET /agent_run/{run_id} for your clip agent's id, so the agent can run that workflow and check on it but cannot publish to social accounts, delete agents, or remove connections. Every call it makes is logged.

How do I schedule a clip to social media through Jentic?

Search Jentic for 'schedule a social post with Mosaic', load the POST /social/post operation, and execute it with post text, media_urls, platforms or destinations from GET /social/connections, and a future schedule_date. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Mosaic So Mosaic AI API

AI ReadinessAI-Aware (B-)61/100

See full scorecard

Official vendor OpenAPI document · agent-readyMediaVideo Processingbearer, apiKey56 EndpointsREST

For Agents

Create and run Mosaic AI video editing agents on uploaded or linked videos, track each run's nodes, and publish or schedule the results to connected social accounts with post analytics.

Use for: Run my clip-cutting agent on this YouTube video URL, Check whether the video edit run has finished, I need to upload a video file before editing it, Schedule the finished clip to TikTok and Instagram for tomorrow

Not supported: Does not stream live video, host a video player, or sell ad placements. Use for running Mosaic AI video editing workflows and publishing their output only.

The Mosaic AI API builds and runs AI video editing workflows, called agents, made of node types such as video inputs, AI avatar, video generation, audio generation, and image generation tiles. A run takes video_inputs, uploaded video IDs, or video URLs, reports per-node status, can be resumed or cancelled, and can send status updates to a callback_url. Agents can also be triggered by new uploads on watched YouTube channels. Finished clips can be published or scheduled to connected X, LinkedIn, Instagram, Facebook, TikTok, and YouTube accounts, with per-post analytics and comments, and shared stores hold reusable key-value entries for workflows.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: C-Signals: 4

94%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

10%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

54%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C-Signals: 4

47%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

57%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

93%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: CSignals: 1

55%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

75%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Mosaic AI API to your agent

Capabilities

Start building with Mosaic AI API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Mosaic So Mosaic AI API

Jentic AI Readiness Score

Mosaic AI API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness