MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
Instagram MCP — 23 tools for Instagram Graph API: posts, DMs, stories, reels, analytics.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"instagram": {
"command": "npx",
"args": [
"-y",
"@mcpware/instagram-mcp"
],
"env": {
"INSTAGRAM_ACCESS_TOKEN": "your-value",
"INSTAGRAM_ACCOUNT_ID": "your-value",
"INSTAGRAM_API_VERSION": "your-value"
}
}
}
}Run this in your terminal
claude mcp add instagram --env INSTAGRAM_ACCESS_TOKEN=your-value --env INSTAGRAM_ACCOUNT_ID=your-value --env INSTAGRAM_API_VERSION=your-value -- npx -y @mcpware/instagram-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"instagram": {
"command": "npx",
"args": [
"-y",
"@mcpware/instagram-mcp"
],
"env": {
"INSTAGRAM_ACCESS_TOKEN": "your-value",
"INSTAGRAM_ACCOUNT_ID": "your-value",
"INSTAGRAM_API_VERSION": "your-value"
}
}
}
}Paste into .vscode/mcp.json in your project
{
"servers": {
"instagram": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mcpware/instagram-mcp"
],
"env": {
"INSTAGRAM_ACCESS_TOKEN": "your-value",
"INSTAGRAM_ACCOUNT_ID": "your-value",
"INSTAGRAM_API_VERSION": "your-value"
}
}
}
}INSTAGRAM_API_VERSION envValues marked secret are keys to your account. Never share them or paste them into a chat.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 5, 2026
The registry name was verified with the GitHub account mcpware, which owns the repo
Code last changed 2 months ago
Uses MIT
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Needs the server’s tool list first; this check starts in the next step
Compared only with servers in this prototype, not the whole registry.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: INSTAGRAM_ACCESS_TOKEN, INSTAGRAM_ACCOUNT_ID
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed 2 months ago, and the latest version (1.0.4) reached the registry 8 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A Model Context Protocol (MCP) server that provides seamless integration with Instagram's Graph API, enabling AI applications to interact with Instagram Business accounts programmatically.
Standard Access (available immediately):
instagram_basicinstagram_content_publishinstagram_manage_insightsinstagram_manage_commentspages_show_listpages_read_engagementpages_manage_metadatapages_read_user_contentbusiness_managementAdvanced Access (requires Meta App Review):
instagram_manage_messages - Required for Direct Messaging features⚠️ Instagram DM Features: Reading and sending Instagram direct messages requires Advanced Access approval from Meta. See INSTAGRAM_DM_SETUP.md for the App Review process.
📖 Quick Start: See AUTHENTICATION_GUIDE.md for a 5-minute setup guide!
This section provides a step-by-step guide to obtain the necessary credentials for the Instagram MCP server.
instagram_basicinstagram_content_publishinstagram_manage_insightspages_show_listpages_read_engagement/me/accountsaccess_token for your page/{page-id}?fields=instagram_business_account # Example OAuth URL
oauth_url = f"https://www.facebook.com/v19.0/dialog/oauth?client_id={app_id}&redirect_uri={redirect_uri}&scope=pages_show_list,instagram_basic,instagram_content_publish,instagram_manage_insights"
# Exchange authorization code for access token
token_url = f"https://graph.facebook.com/v19.0/oauth/access_token?client_id={app_id}&redirect_uri={redirect_uri}&client_secret={app_secret}&code={auth_code}"
Short-lived tokens expire in 1 hour. Convert to long-lived token (60 days):
curl -X GET "https://graph.facebook.com/v19.0/oauth/access_token?grant_type=fb_exchange_token&client_id={app_id}&client_secret={app_secret}&fb_exchange_token={short_lived_token}"
Create a .env file in your project root:
# Facebook App Credentials
FACEBOOK_APP_ID=your_app_id_here FACEBOOK_APP_SECRET=your_app_secret_here
INSTAGRAM_ACCESS_TOKEN=your_long_lived_access_token_here
INSTAGRAM_BUSINESS_ACCOUNT_ID=your_instagram_business_account_id_here
INSTAGRAM_API_VERSION=v19.0 RATE_LIMIT_REQUESTS_PER_HOUR=200 CACHE_ENABLED=true LOG_LEVEL=INFO
Run the validation script to test your credentials:
python scripts/setup.py
Or test manually:
import os
import requests
access_token = os.getenv('INSTAGRAM_ACCESS_TOKEN') response = requests.get(f'https://graph.facebook.com/v19.0/me?access_token={access_token}') print(response.json())
Long-lived tokens expire after 60 days. Implement automatic refresh:
# Check token validity
def check_token_validity(access_token): url = f"https://graph.facebook.com/v19.0/me?access_token={access_token}" response = requests.get(url) return response.status_code == 200
def refresh_long_lived_token(access_token, app_id, app_secret): url = f"https://graph.facebook.com/v19.0/oauth/access_token" params = { 'grant_type': 'fb_exchange_token', 'client_id': app_id, 'client_secret': app_secret, 'fb_exchange_token': access_token } response = requests.get(url, params=params) return response.json().get('access_token')
Error: "Invalid OAuth access token"
Error: "Instagram account not found"
Error: "Insufficient permissions"
Rate Limiting Issues
git clone <repository-url>
cd ig-mcp
pip install -r requirements.txt
cp .env.example .env
# Edit config.json with your specific settings
INSTAGRAM_ACCESS_TOKEN=your_long_lived_access_token
FACEBOOK_APP_ID=your_facebook_app_id FACEBOOK_APP_SECRET=your_facebook_app_secret INSTAGRAM_BUSINESS_ACCOUNT_ID=your_instagram_business_account_id
Add this to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": { "instagram": { "command": "python", "args": ["/path/to/ig-mcp/src/instagram_mcp_server.py"], "env": { "INSTAGRAM_ACCESS_TOKEN": "your_access_token" } } } }
Can you get my Instagram profile information?
Show me my last 5 Instagram posts and their engagement metrics
Upload this image to my Instagram account with the caption "Beautiful sunset! #photography #nature"
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
server_params = StdioServerParameters( command="python", args=["src/instagram_mcp_server.py"] )
async with stdio_client(server_params) as (read, write): async with ClientSession(read, write) as session: await session.initialize()
result = await session.call_tool("get_profile_info", {}) print(result)