# Lection (remote · www.lection.app)

Search YouTube videos, channel uploads and comments as tables; manage Lection schedules.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

> **Recent critical change**: Authorization (2026-10-14). See the changelog below before you install this server.

## Components

- remote · `www.lection.app`: 70/100 (this document), [markdown](https://verifymcp.io/servers/eteleieto-lection-mcp/www.md), [page](https://verifymcp.io/servers/eteleieto-lection-mcp/www)

## Channel facts

- Endpoint: `https://www.lection.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (pause_schedule).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1268 tokens (~105/item across 12 items; 11 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% of tool parameters carry a description.
  - Structured output schemas are declared (27% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Lection MCP server?

Lection is a hosted endpoint at https://www.lection.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http eteleieto-lection-mcp 'https://www.lection.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "eteleieto-lection-mcp": {
      "url": "https://www.lection.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "eteleieto-lection-mcp": {
      "type": "http",
      "url": "https://www.lection.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.eteleieto-lection-mcp]
url = "https://www.lection.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "eteleieto-lection-mcp": {
      "type": "remote",
      "url": "https://www.lection.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add eteleieto-lection-mcp --url 'https://www.lection.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  eteleieto-lection-mcp:
    url: "https://www.lection.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "eteleieto-lection-mcp": {
      "Transport": "http",
      "Url": "https://www.lection.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add eteleieto-lection-mcp -t streamable-http -u 'https://www.lection.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "eteleieto-lection-mcp": {
      "type": "http",
      "url": "https://www.lection.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 69, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-14 (score 68, +64)

- [critical regression] Authorization: unverified → fail
- [security regression] DNSSEC: unverified → fail
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 88
- [functional] First check of Destructive annotations: pass
- [functional] First check of Capabilities: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 27
- [functional] First check of Schema quality: good

### 2026-10-13 (score 4)

First indexed and scored.

## MCP tools (11)

### `youtube_search` (~132 tokens)

Search YouTube videos

Search YouTube for videos by keyword, like "n8n automation tutorial" or "best budget laptops 2026". Returns up to 20 videos with title, channel, view count, upload date, duration and URL. Use it for content research, finding competitors and spotting popular topics. To list videos from one specific channel use youtube_channel_videos instead.

Input parameters:

- `maxRows` (integer): How many rows to return (1-20, default 20). The free ChatGPT app is capped at 20.
- `query` (string, required): Search keywords, exactly as you would type them into YouTube.

Output parameters:

- `count` (number): Number of rows returned
- `error` (string)
- `fullToolUrl` (string): Lection page for running this at full scale with exports and schedules
- `rows` (array): Result rows
- `tool` (string)

### `youtube_channel_videos` (~138 tokens)

List a YouTube channel's videos

List the latest videos on one YouTube channel, given its @handle or URL (for example "@OpenAI" or https://www.youtube.com/@OpenAI). Returns up to 20 recent uploads with title, upload date, view count, duration and URL. Use it to audit a creator or competitor channel. To search all of YouTube by keyword use youtube_search.

Input parameters:

- `channel` (string, required): Channel @handle (e.g. "@OpenAI") or channel URL.
- `maxRows` (integer): How many rows to return (1-20, default 20). The free ChatGPT app is capped at 20.

Output parameters:

- `count` (number): Number of rows returned
- `error` (string)
- `fullToolUrl` (string): Lection page for running this at full scale with exports and schedules
- `rows` (array): Result rows
- `tool` (string)

### `youtube_comments` (~152 tokens)

Get comments on a YouTube video

Fetch top-level comments from one public YouTube video, given its URL. Returns up to 20 top comments with author, text, like count, reply count, date and the author's channel link. Use it for audience sentiment, feedback mining and finding engaged commenters. Needs a specific video URL; to find videos first use youtube_search.

Input parameters:

- `maxRows` (integer): How many rows to return (1-20, default 20). The free ChatGPT app is capped at 20.
- `url` (string, required): Full YouTube video URL, e.g. https://www.youtube.com/watch?v=dQw4w9WgXcQ (youtu.be and /shorts/ links also work).

Output parameters:

- `count` (number): Number of rows returned
- `error` (string)
- `fullToolUrl` (string): Lection page for running this at full scale with exports and schedules
- `rows` (array): Result rows
- `tool` (string)

### `lection_browser_tools_info` (~100 tokens)

Instagram and LinkedIn exports (browser extension)

Explain how to export data from Instagram (comments, followers, following, posts) or LinkedIn (connections) with Lection. These sites require login, so they run in the user's own browser through the Lection Chrome extension rather than inside ChatGPT. Call this whenever the user asks for Instagram or LinkedIn data; it returns the install link and the right tool page.

Input parameters:

- `platform` (string, required): Which site the user wants data from.

### `my_lection_account` (~44 tokens)

My Lection plan and limits

Show the linked user's Lection plan, how many schedules they can run, allowed delivery destinations and available cloud credits. Use before scheduling or when a plan limit is hit.

### `list_my_saved_scrapes` (~67 tokens)

List my saved scrapes

List the user's most recent saved scrapes in Lection (title, page, row count, id). A saved scrape is the starting point for schedule_extraction and get_run_results.

Input parameters:

- `limit` (integer): How many recent saved scrapes to list (1-20).

### `get_run_results` (~112 tokens)

Get saved scrape or run results

Fetch the rows of one of the user's saved scrapes or scheduled runs by id and show them as a table. Use list_my_saved_scrapes or list_my_runs first to find the id.

Input parameters:

- `id` (string, required): Id of a saved scrape (from list_my_saved_scrapes) or of a scheduled run (from list_my_runs).
- `kind` (string, required): Whether `id` is a saved scrape or a scheduled run.
- `maxRows` (integer): Rows to return (1-200).

### `list_my_schedules` (~47 tokens)

List my schedules

List the user's scheduled extractions: name, cadence, destination, next run and last status.

Input parameters:

- `limit` (integer)
- `status` (string): Filter by schedule status.

### `list_my_runs` (~51 tokens)

List my scheduled runs

List recent runs of the user's schedules with status, row counts and errors.

Input parameters:

- `limit` (integer)
- `scheduleId` (string): Only runs of this schedule.
- `status` (string)

### `schedule_extraction` (~293 tokens)

Schedule a saved scrape

Create a recurring schedule (hourly, daily or weekly) that re-runs one of the user's saved scrapes and delivers each run to email, a Google Sheet or a webhook. This creates a recurring job in the user's Lection account and may use cloud credits: confirm the saved scrape, cadence and destination with the user before calling. Respects the user's plan limits and returns a clear message if one is reached.

Input parameters:

- `cadence` (string, required): How often to run.
- `destination` (string): Where each run is delivered. google_sheet needs the user to have connected Google Sheets in Lection; webhook needs webhookUrl.
- `name` (string, required): Schedule name, at least 3 characters.
- `savedScrapeId` (string, required): Id of an existing saved scrape in the user's Lection account (from list_my_saved_scrapes). The schedule re-runs that scrape.
- `spreadsheetUrl` (string): Google Sheet URL (destination google_sheet).
- `timeOfDay` (string): HH:MM (24h) in the given timezone, for daily/weekly. Default 09:00.
- `timezone` (string): IANA timezone, e.g. "America/Chicago". Default UTC.
- `webhookUrl` (string): HTTPS webhook URL (destination webhook).
- `weekday` (integer): 0=Sunday .. 6=Saturday, for weekly. Default 1 (Monday).

### `pause_schedule` (~56 tokens)

Pause a schedule

Pause one of the user's schedules so it stops running. The user can resume it from the Lection dashboard. Confirm with the user first.

Input parameters:

- `scheduleId` (string, required): Id of the schedule to pause (from list_my_schedules).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/eteleieto-lection-mcp/www#diagnostics

## Score history

- 2026-10-18: 70
- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 69
- 2026-10-14: 68
- 2026-10-13: 4

## Common questions

### What is the Lection MCP server?

Lection is an MCP server listed in the public MCP registry as io.github.eteleieto/lection-mcp. Search YouTube videos, channel uploads and comments as tables; manage Lection schedules. This page covers its hosted endpoint (https://www.lection.app/mcp).

### Is the Lection MCP server safe to use?

Lection scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Lection MCP server expose?

Lection exposes 11 tools: youtube_search, youtube_channel_videos, youtube_comments, lection_browser_tools_info, my_lection_account, and 6 more. Their descriptions and schemas cost roughly 1,192 tokens of context every time the server is loaded.

### Does the Lection MCP server require authentication?

No. We connected to Lection without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Lection MCP server still maintained?

Lection is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.lection.app/mcp
- Repository: https://github.com/eteleieto/lection-mcp
- Website: https://www.lection.app/
- Changelog RSS feed: https://verifymcp.io/servers/eteleieto-lection-mcp/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/eteleieto-lection-mcp/www.json
- HTML version of this page: https://verifymcp.io/servers/eteleieto-lection-mcp/www