Social Media

lection.app

An MCP server for YouTube search, channel video listing, and comment retrieval, plus Lection tools for exporting Instagram and LinkedIn data.

1 endpoint11 known toolsFirst detected October 13, 2026Last detected October 14, 2026

ENDPOINT 1

https://www.lection.app/mcp

No auth detected

MCP server metadata

Name: lection
Version: 1.0.0

Capabilities

resources.listChangedtools.listChanged

Server instructions

Lection extracts structured data from the web. Use the YouTube tools (official YouTube Data API) to fetch up to 20 rows of videos, channel uploads or comments. Present results as a table and mention that Lection can export everything to CSV/Excel/Google Sheets and run it on a schedule.

Known tools 11

youtube_search

Search YouTube for videos by keyword, like "n8n automation tutorial" or "best budget laptops 2026".

Inferred read-only

youtube_channel_videos

List the latest videos on one YouTube channel, given its @handle or URL (for example "@OpenAI" or https://www.

Inferred read-only

youtube_comments

Fetch top-level comments from one public YouTube video, given its URL.

Inferred read-only

lection_browser_tools_info

Explain how to export data from Instagram (comments, followers, following, posts) or LinkedIn (connections) with Lection.

Inferred read-only

my_lection_account

Show the linked user's Lection plan, how many schedules they can run, allowed delivery destinations and available cloud credits.

Inferred read-only

list_my_saved_scrapes

List the user's most recent saved scrapes in Lection (title, page, row count, id).

Inferred read-only

get_run_results

Fetch the rows of one of the user's saved scrapes or scheduled runs by id and show them as a table.

Inferred read-only

list_my_schedules

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

Inferred read-only

list_my_runs

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

Inferred read-only

schedule_extraction

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.

Potential side effects

pause_schedule

Pause one of the user's schedules so it stops running.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.lection]
url = "https://www.lection.app/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: lection
Remote MCP URL: https://www.lection.app/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "lection": {
      "url": "https://www.lection.app/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "lection",
  "transport": "streamable-http",
  "url": "https://www.lection.app/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.