The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Instagram Scraper: Reels to Text, Posts, Comments, No Login listing page.
Connect two public-data scrapers to ChatGPT, Claude, Claude Code, Cursor, VS Code, Windsurf, n8n or your own agent in about a minute. No YouTube API key, no Instagram account, no shared keys: you sign in to your own Apify account with OAuth and pay per result.
| Actor | What it is good at | Price (2026-09-26) |
|---|---|---|
| YouTube Scraper | Video stats, top comments and a dislike estimate in one row, from search terms, channels, playlists or video URLs. No API quota. | $2.00 per 1,000 videos, comments included |
| Instagram Scraper | Reels to text, plus public creator signals: engagement, paid-partnership flags, related accounts, business contacts in the bio. No login. | $1.90 per 1,000 results, transcripts $0.004 per minute |
Both are published by Yugenox Corporation on the Apify Store. This repo holds no server code:
Apify hosts the MCP server at mcp.apify.com, and the URLs below pin it to these two Actors.
| Name | Tools | URL |
|---|---|---|
yugenox-social | both Actors | https://mcp.apify.com/?tools=fetch-actor-details,yugenox/instagram-scraper,yugenox/youtube-scraper |
yugenox-youtube | YouTube only | https://mcp.apify.com/?tools=fetch-actor-details,yugenox/youtube-scraper |
yugenox-instagram | Instagram only | https://mcp.apify.com/?tools=fetch-actor-details,yugenox/instagram-scraper |
Each server exposes yugenox--youtube-scraper and/or yugenox--instagram-scraper, plus
fetch-actor-details (lets the agent read the README and current price before a paid run)
and Apify's run helpers get-actor-run, get-dataset-items, get-key-value-store-record
and abort-actor-run.
Sign-in: the first tool call opens an Apify sign-in page (OAuth). Runs bill to the account you sign in with. Never paste a token into one of these URLs.
Then run /mcp, pick yugenox-social and authenticate in the browser.
Or install the plugin, which adds the same server plus two skills that state the cost before each run:
The plugin folder, plugins/yugenox-social-data, also follows the
Agent Plugins 1.0 format (plugin.json, mcp.json, skills/), so
other clients that load Agent Plugins can install the same server and skills from it.
Settings → Connectors → Add custom connector. Name it yugenox-social, paste the server
URL, click Add, then Connect and sign in to Apify. Leave the OAuth client fields empty;
Apify registers the client automatically.
ChatGPT on the web → Settings → Apps & Connectors → Advanced settings → turn on Developer mode. Back in Apps & Connectors, click Create, paste the server URL, set Authentication to OAuth, confirm, and sign in to Apify. In a chat, enable the connector from the + menu under Developer mode. (Menu labels move between ChatGPT releases; the flow stays the same.)
YouTube only: install · Instagram only: install
Or add it to ~/.cursor/mcp.json:
Cursor then asks you to sign in: open Settings → MCP and click the login button next to the server to finish the Apify sign-in.
YouTube only: install · Instagram only: install
Or add it to .vscode/mcp.json (note the servers key):
VS Code asks you to sign in to Apify when the server starts.
Add to ~/.codeium/windsurf/mcp_config.json, then refresh the MCP panel and sign in:
Add an AI Agent node, then attach an MCP Client Tool:
yugenox--youtube-scraper, yugenox--instagram-scraper, fetch-actor-detailsAny MCP client that only runs local (stdio) servers can use the mcp-remote bridge, which
opens the Apify sign-in in your browser:
Every link and config above is generated from one file: install-links.json.
Minimal, runnable examples in examples/. Each reads your own APIFY_TOKEN
from the environment and sends it as an Authorization header.
| Framework | Example | How it connects |
|---|---|---|
| LangChain / LangGraph | langgraph/youtube_langgraph.py | ApifyActorsTool("yugenox/youtube-scraper") |
| CrewAI | crewai/instagram_crew.py | ApifyActorsTool(actor_name="yugenox/instagram-scraper") |
| LlamaIndex | llamaindex/youtube_comments_mcp.py | BasicMCPClient + McpToolSpec on the pinned URL |
| OpenAI Agents SDK | openai-agents/social_agent.py | MCPServerStreamableHttp on the pinned URL |
| Vercel AI SDK | vercel-ai-sdk/youtube-agent.ts | createMCPClient from @ai-sdk/mcp |
| Claude Agent SDK | claude-agent-sdk/instagram-agent.ts | mcpServers with type: "http" |
You pay Apify per result, from your own account. Prices below are the Store list prices on 2026-09-26; the Actor pages are the source of truth.
streamers/youtube-scraper plus its separate streamers/youtube-comments-scraper is $4.40
at their Free-tier prices ($0.40 for videos + $4.00 for 2,000 comments).error field explaining why.Good habit for agents: set maxItems on every call and say the estimate before running.
The plugin skills and example prompts do this.
YouTube:
Instagram:
includeSubtitles on, the available
subtitle languages are listed (best-effort); subtitle text is not reliable.duration is filled on search rows only for now; channel, playlist and
video-URL rows leave it empty.Listed in the official MCP Registry
as io.github.ArpitGandhi1934/yugenox-social-data, io.github.ArpitGandhi1934/yugenox-youtube-scraper
and io.github.ArpitGandhi1934/yugenox-instagram-scraper. The entries live in
registry/ and are published by GitHub Actions on each version tag.
Built by Yugenox Corporation, Toronto. Questions or a bug: open an issue here or on the Actor's Issues tab on Apify. Uses public data only. Not affiliated with or endorsed by YouTube, Google, Instagram, Meta, OpenAI or Anthropic.
MIT licensed (this repo's configs and examples). The Actors are paid services on Apify.