---
title: "Vidext — Agent-driven training production for frontline teams"
description: "When to use Vidext, how an agent starts, the constraints it must respect, and the machine-readable endpoints."
canonical: "https://app.vidext.io/agents.md"
last-updated: "2026-10-28T10:09:04.469Z"
---

# Vidext — Agent-driven training production for frontline teams

## When To Use Vidext

- The user wants organizational documents, decks, transcripts, or a website turned into a structured training module or learning path.
- The user wants onboarding, compliance, product, partner, or customer-education content generated and kept current from source material rather than authored by hand.
- The user needs short interactive video lessons — narrated screens, an optional presenter, and comprehension checks — built from that material.
- Learners need comprehension checks and a tutor that answers from their assigned course first, knows the scene they are on and their progress, and labels any public-web research it runs as coming from outside the course.
- An agent needs to search organization knowledge, list Vidext modules, or plan and build modules with the Vidext author on a user's behalf through the Vidext MCP server.

Not a fit:

- Hosting enrollments, gradebooks, or assignments as an LMS system of record (Vidext complements an LMS, it does not replace one).
- Recording a desktop app, or a web app on a private network: the agents record narrated tutorials only of web apps on the public internet.
- A general-purpose assistant for learners: the tutor declines requests unrelated to their course.

## How To Start

1. Read [llms.txt](https://app.vidext.io/llms.txt) for product context.
2. Discover the MCP server at [/.well-known/mcp](https://app.vidext.io/.well-known/mcp).
3. Read [/developers](https://app.vidext.io/developers) for auth and rate-limit guidance.
4. Authenticate with OAuth 2.1 + PKCE.
5. Select the narrowest typed tool: `search_knowledge`, `read_knowledge_source`, or `list_modules` to read, or `author_send` and the other author tools to plan and build modules with the Vidext author.
6. If already operating inside an authenticated Vidext browser page, use the browser WebMCP navigation/module tools for local UI actions.

## Important Constraints

- Only organization admins and members can connect over MCP; learners and people whose request to join is still pending are refused.
- Access is scoped by organization and role: admins and members see every module in the organization and its processed sources, with no per-team filtering.
- Grounding and workflow actions are scoped to the authenticated organization, the token's scopes, and the available tools.

## Machine-Readable Endpoints

- [llms.txt](https://app.vidext.io/llms.txt)
- [llms-full.txt](https://app.vidext.io/llms-full.txt)
- [developers](https://app.vidext.io/developers)
- [openapi.json](https://app.vidext.io/openapi.json)
- [server.json](https://app.vidext.io/server.json)
- [pricing.md](https://app.vidext.io/pricing.md)
- [index.md](https://app.vidext.io/index.md)
- [compare](https://app.vidext.io/compare)
- [alternatives](https://app.vidext.io/alternatives)
- [AI learning path generator for employee training](https://app.vidext.io/best-ai-learning-path-generator-for-employee-training)
- [card.json](https://app.vidext.io/card.json)
- [MCP endpoint](https://app.vidext.io/api/mcp)

## Documentation

- [Documentation](https://docs.vidext.io) — product, learner, and API docs with a markdown twin for every page (append `.md`).
- [Integration quickstart: connect an AI client](https://docs.vidext.io/docs/api/connect-an-ai-client) — setup instructions for Claude, Cursor, and Codex. [Markdown](https://docs.vidext.io/docs/api/connect-an-ai-client.md).
- [API and agents docs](https://docs.vidext.io/docs/api) — what is public, environments, quickstarts.
- [MCP server reference](https://docs.vidext.io/docs/api/mcp) — endpoint contract, authentication, tools, errors and limits.
- [Docs llms.txt](https://docs.vidext.io/llms.txt) and [llms-full.txt](https://docs.vidext.io/llms-full.txt) — the whole documentation set for LLM ingestion.