🤖 Instagram MCP AI agent – read, reply & manage comments with GPT-4o

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Instagram AI Agent with MCP Server – Built for Smart Engagement and Automation Hi! I’m Amanda I build intelligent automations with n8n and Make. This powerful workflow was designed to help te...

Best for

Social Media automation workflows
AI Chatbot automation workflows
advanced n8n builders looking for reusable templates

Tools used

@n8n/n8n-nodes-langchain.chattrigger, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.memorybufferwindow, @n8n/n8n-nodes-langchain.mcptrigger, @n8n/n8n-nodes-langchain.mcpclienttool, @n8n/n8n-nodes-langchain.toolhttprequest, n8n-nodes-base.set, n8n-nodes-base.stickynote

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Amanda Benks.

Original n8n.io source

1.1 Workflow description

Title: 🤖 Instagram MCP AI agent – read, reply & manage comments with GPT-4o
Workflow name: 🤖 Instagram MCP AI agent – read, reply & manage comments with GPT-4o

🤖 Instagram AI Agent with MCP Server – Built for Smart Engagement and Automation

Hi! I’m Amanda 🥰

I build intelligent automations with n8n and Make.
This powerful workflow was designed to help teams automatically handle Instagram interactions with AI. Using Meta Graph API, LangChain, MCP Server, and GPT-4o, it allows your AI agent to search for posts, read captions, fetch comments, and even reply or message followers, all through structured tools.

🔧 What the workflow does

Searches for recent media using Instagram ID and access token
Reads and extracts captions or media URLs
Fetches comments and specific replies from each post
Replies to comments automatically with GPT-generated responses
Sends direct messages to followers who commented
Maps user input and session to keep memory context via LangChain
Communicates via Server-Sent Events (SSE) using your MCP Server URL

🧰 Nodes & Tech Used

LangChain Agent + Chat Model with GPT-4o
Memory Buffer for session memory
toolHttpRequest to search media, comments, and send replies
MCP Trigger and MCP Tool (custom SSE connection)
Set node for input and variable assignment
Webhook and JSON for Instagram API structure

⚙️ Setup Instructions

Create your Instagram App in Meta Developer Portal
Add your Instagram ID and Access Token in the Set node
Update the MCP Server Tool URL in the MCP Instagram node
- Use your n8n server URL (e.g. https://yourdomain.com/mcp/server/instagram/sse)
Trigger the workflow using the included LangChain Chat Trigger
Interact via text to ask the agent to:
- “Get latest posts”
- “Reply to comment X with this message”
- “Send DM to this user about...”

👥 Who this is for

Social media teams managing multiple comments
Brands automating engagement with followers
Agencies creating smart, autonomous digital assistants
Developers building conversational Instagram bots

✅ Requirements

Meta Graph API access
Instagram Business account
n8n instance (Cloud or Self-hosted)
MCP Server configured (SSE Endpoint enabled)
OpenAI API Key (for GPT-4o + LangChain)

🌐 Want to use this workflow?

❤️ Buy workflows: https://iloveflows.com
☁️ Try n8n Cloud: https://n8n.partnerlinks.io/amanda

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When chat message received

Type / Role: @n8n/n8n-nodes-langchain.chatTrigger - chatTrigger
Config choices: Version 1.1

Block 2 - AI Agent

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 1.9

Block 3 - Simple Memory

Type / Role: @n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices: Version 1.3

Block 4 - 🗂️ MCP Instagram

Type / Role: @n8n/n8n-nodes-langchain.mcpTrigger - mcpTrigger
Config choices: Version 1

Block 5 - MCP Instagram

Type / Role: @n8n/n8n-nodes-langchain.mcpClientTool - mcpClientTool
Config choices: Version 1

Block 6 - Search Media

Type / Role: @n8n/n8n-nodes-langchain.toolHttpRequest - toolHttpRequest
Config choices: Version 1.1

Block 7 - Instagram Mapping

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 8 - Media Details

Type / Role: @n8n/n8n-nodes-langchain.toolHttpRequest - toolHttpRequest
Config choices: Version 1.1

Block 9 - Search Comment

Type / Role: @n8n/n8n-nodes-langchain.toolHttpRequest - toolHttpRequest
Config choices: Version 1.1

Block 10 - Reply Comment

Type / Role: @n8n/n8n-nodes-langchain.toolHttpRequest - toolHttpRequest
Config choices: Version 1.1

Block 11 - Send Direct Message

Type / Role: @n8n/n8n-nodes-langchain.toolHttpRequest - toolHttpRequest
Config choices: Version 1.1

Block 12 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 13 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 14 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 15 - Chat Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1.2

Block 16 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 17 - Sticky Note4

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

3. Summary Table

Workflow	🤖 Instagram MCP AI agent – read, reply & manage comments with GPT-4o
Complexity	advanced
Nodes	17
Categories	Social Media, AI Chatbot
Author	Amanda Benks
Published	06 May 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/3896/3896.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Social Media workflows AI Chatbot workflows

Frequently asked questions

What does 🤖 Instagram MCP AI agent – read, reply & manage comments with GPT-4o do?

Instagram AI Agent with MCP Server – Built for Smart Engagement and Automation Hi! I’m Amanda I build intelligent automations with n8n and Make. This powerful workflow was designed to help te...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Social Media, AI Chatbot use case.

Amanda Benks

17 workflows

Nodes

@n8n/n8n-nodes-langchain.chattrigger @n8n/n8n-nodes-langchain.agent @n8n/n8n-nodes-langchain.memorybufferwindow @n8n/n8n-nodes-langchain.mcptrigger @n8n/n8n-nodes-langchain.mcpclienttool @n8n/n8n-nodes-langchain.toolhttprequest n8n-nodes-base.set n8n-nodes-base.stickynote

Complexity

advanced

Published 06 May 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/3896/3896.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Promote YouTube uploads to social channels with DeepSeek and Posta

## Quick overview This workflow fetches the latest video from a YouTube channel feed, generates platform-specific promo captions with DeepSeek, and creates draft promotion posts in Posta for active social media accounts. You can automatically promote your videos to all your social media. Add a "publish" at the end for auto-post. ## How it works 1. Runs manually when you click “Execute workflow”. 2. Fetches your YouTube channel RSS feed over HTTP, parses the XML, and extracts the latest video’s title, description, thumbnail URL, and link. 3. Downloads the video thumbnail and uploads it to Posta to create a reusable media asset. 4. Retrieves your social accounts from Posta, keeps only active accounts, and de-duplicates them to one account per platform. 5. Combines the latest video data with each target platform and asks DeepSeek (via an n8n LangChain LLM chain) to write a tailored promotional caption per platform. 6. Tags each generated caption with its platform and merges it back to the matching Posta social account. 7. Creates a draft Posta post per selected account, attaching the uploaded thumbnail and the platform-specific caption and video link. 8. (Optional) Add a "publish a post" at the end to automatically post to the social media channels (If you are feeling brave and trust the LLM), ## Setup 1. Add a Posta API credential and select it in the Posta nodes that list accounts, upload media, and create posts. 2. Add a DeepSeek API credential and select it in the DeepSeek Chat Model node. 3. Update the YouTube channel feed URL (channel_id) in the HTTP request that downloads the YouTube feed. 4. Review your Posta social accounts to ensure the intended accounts are marked active and have the correct platform values for de-duplication. ## Additional info Video explanation: https://youtu.be/tTWaYb71YyA

View

Post scheduled Threads updates from Google Sheets with error tracking

## Quick overview This workflow runs hourly to read the next pending post from Google Sheets, publishes it to Threads via the Threads Graph API, and then updates the sheet with published or failed status plus timestamps and error details. ## How it works 1. Runs every hour on a schedule. 2. Reads the first row in Google Sheets where the status column equals pending. 3. Retrieves the authenticated Threads account’s user ID from the Threads Graph API. 4. Creates a Threads text post container using the content from the pending Google Sheets row. 5. Publishes the post to Threads and updates the same Google Sheets row as published with posted_at and updated_at timestamps. 6. If any Threads API call fails, records the error message and marks the corresponding Google Sheets row as failed with an updated_at timestamp. ## Setup 1. Create a Meta app and generate a Threads access token, then add it to an HTTP Header Auth credential used for the Threads Graph API requests. 2. Set up a Google Sheets Service Account credential in n8n and share your target spreadsheet with the service account email. 3. Replace the placeholder Google Sheet ID in all Google Sheets nodes and confirm the sheet name is Sheet1 (or update it to match your sheet). 4. Ensure your sheet has the required columns (row_number, content, status, posted_at, updated_at, error_message) and set status to pending for posts you want published.

View

Send a daily product newsletter with Google Sheets and Gmail

## Quick Overview This workflow runs daily at 08:00, pulls products scheduled for today from Google Sheets, generates an HTML newsletter email, and sends it to each subscriber via Gmail. ## How it works 1. Runs every day at 08:00 on a schedule. 2. Reads all rows from the `newsletter_products` sheet in Google Sheets. 3. Keeps only products whose `send_date` matches today’s date and stops if none are found. 4. Builds an HTML email and subject line containing a card for each product (image, description, and optional referral link). 5. Reads the subscriber list from the `newsletter_recipients` sheet in Google Sheets. 6. Sends the generated newsletter to each recipient individually using Gmail. ## Setup 1. Create or copy a Google Sheets document with `newsletter_products` (including a `send_date` column) and `newsletter_recipients` (including an `email` column). 2. Add a Google Sheets OAuth2 credential in n8n and paste your Google Sheet ID into the Config step. 3. Add a Gmail OAuth2 credential and confirm the sender mailbox to use for sending the newsletter. 4. Add products and recipients to the sheet, run a test execution, and adjust the schedule/timezone if needed before activating.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

🤖 Instagram MCP AI agent – read, reply & manage comments with GPT-4o

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

🤖 Instagram AI Agent with MCP Server – Built for Smart Engagement and Automation

Hi! I’m Amanda 🥰

🔧 What the workflow does

🧰 Nodes & Tech Used

⚙️ Setup Instructions

👥 Who this is for

✅ Requirements

🌐 Want to use this workflow?

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - When chat message received

Block 2 - AI Agent

Block 3 - Simple Memory

Block 4 - 🗂️ MCP Instagram

Block 5 - MCP Instagram

Block 6 - Search Media

Block 7 - Instagram Mapping

Block 8 - Media Details

Block 9 - Search Comment

Block 10 - Reply Comment

Block 11 - Send Direct Message

Block 12 - Sticky Note

Block 13 - Sticky Note1

Block 14 - Sticky Note2

Block 15 - Chat Model

Block 16 - Sticky Note3

Block 17 - Sticky Note4

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions