Tutorializer

Connect Tutorializer to Claude, ChatGPT and MCP clients

Tutorializer provides one hosted Model Context Protocol endpoint for AI assistants. It uses OAuth, so every person signs in with their own Tutorializer account and can only reach projects in organizations where they have a live role.

Ask an assistant to inspect projects, tutorial definitions, rendered videos and voiceover segments; audit locale and device coverage; or show the interactive project and tutorial cards. Write tools can create a project, maintain pronunciation rules, or delete one speech or video.

{ "mcpServers": { "tutorializer": { "type": "http", "url": "https://mcp.tutorializer.com/mcp" } } }

Use the production URL above in any client that accepts a remote Streamable HTTP MCP server. OAuth discovery, dynamic client registration and PKCE are handled during connection; do not paste an API key into the MCP configuration.

Read tools use the tutorializer:read scope. State-changing tools use tutorializer:write and declare whether they are destructive and idempotent so compatible hosts can request approval. Deletion removes stored media, so review the exact target before approving it. AI speech and video generation remain in the Tutorializer dashboard and publishing CLI rather than this public connector.

The connector returns bounded projections rather than raw database documents. It never exposes organization ownership fields, vendor dictionary handles, speech alignment arrays, credentials or tokens.

The Tutorializer REST API lets your own backend work with the same content the dashboard does: the projects you record tutorials for, the tutorials themselves, the videos rendered from them and the speech clips their voice-overs are synthesized from.

Open the Tutorializer dashboard and create an API key under API keys. The secret is shown when the key is created and is never returned by the endpoints that list or read keys — an organization admin can reveal it again from the dashboard, but only after re-entering their password. A key belongs to a single organization, so the organization is implied by the key and never has to be sent.

Authenticate every request with HTTP Basic auth carrying only the key secret, base64-encoded, in the Authorization header.

# The Authorization header is HTTP Basic auth carrying only the key secret, # with no username and no colon. Authorization: Basic $(printf %s YOUR_API_KEY_SECRET | base64)

Every endpoint lives underhttps://api.tutorializer.com. Requests made with a key are rate limited per key; going over the limit returns 429.

List your projects, read the tutorials of one of them, then read the videos rendered for a single tutorial.

# List the projects of your organization curl https://api.tutorializer.com/api/projects \ -H "Authorization: Basic $(printf %s YOUR_API_KEY_SECRET | base64)" # List the tutorials of one of those projects curl "https://api.tutorializer.com/api/tutorials?projectId=PROJECT_ID" \ -H "Authorization: Basic $(printf %s YOUR_API_KEY_SECRET | base64)" # List the rendered videos of a single tutorial curl "https://api.tutorializer.com/api/videos?projectId=PROJECT_ID&tutorialId=TUTORIAL_ID" \ -H "Authorization: Basic $(printf %s YOUR_API_KEY_SECRET | base64)"

Browse the full API reference— every endpoint with its parameters, request body, responses and required scope.

The CLI is open source atgithub.com/tutorializer/cliand published astutorializer on npm. Run any command with --help to see its options.

Tutorializer ships Agent Skills — guides following theagentskills.io standardthat teach coding agents how to audit and maintain your tutorial library with the tutorializer CLI and the MCP connector, instead of guessing at commands and tools.

# Install the Tutorializer skills into your coding agent npx skills add tutorializer/skills

The skills are open source atgithub.com/tutorializer/skills. Claude users can also install the Tutorializer Claude plugin, which bundles the connector together with the skills:github.com/tutorializer/claude-plugin.

POST https://your-server.com/tutorializer-webhook { "event": "video.created", "timestamp": 1719000000, "data": { "...": "..." } }

import crypto from 'node:crypto' // body must be the RAW request body, byte for byte function verify(header, body, secret) { const [t, v1] = (header || '').split(',').map(part => part.split('=')[1]) if (!t || !v1) return false const expected = crypto .createHmac('sha256', secret) .update(\${t}.${body}\) .digest('hex') // timingSafeEqual throws on a length mismatch, so a malformed signature // has to be rejected before the comparison rather than by it. if (v1.length !== expected.length) return false return crypto.timingSafeEqual(Buffer.from(v1), Buffer.from(expected)) }

Delivery is one best-effort attempt with a five second timeout and no retries, so respond 2xx quickly and do the work asynchronously. An endpoint that fails twenty times in a row is disabled automatically and has to be re-enabled in the dashboard.

The 1Password MCP server creates a bridge that allows MCP clients such as Codex and Kiro to manage your 1Password Environments with secure authorization prompts.

This is the 1st, easiest, and cheapest PPT, slides, presentation AI generation MCP Server in the world.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

A MCP server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.

Enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.

An MCP server for WordPress plugin audits

Turn your AI assistant into a digital marketing hub that creates, organizes, and analyzes links and QR Codes on demand.

Connect AI clients to Cal.com scheduling through the Model Context Protocol using the hosted server at mcp.cal.com or a local instance.

Sync Calendars, Scheduling Links, AI Executive Scheduling Assistant, Unified Calendar