n8n AI Agent for Comment Management with GPT-4o

This n8n workflow leverages the power of AI to intelligently process and manage comments, likely from platforms like Instagram, using a GPT-4o powered agent. It sets up a sophisticated system where an AI agent can read incoming messages, decide on an appropriate action, and potentially interact with external services via HTTP requests or a Model Context Protocol (MCP) client.

What it does

This workflow defines an AI agent that can:

1. Receive Chat Messages: It is triggered by incoming chat messages, acting as the entry point for new comments or interactions.
2. Process with an AI Agent: An AI Agent node is at the core, designed to interpret the incoming chat messages. This agent is configured with:
   • OpenAI Chat Model (GPT-4o): Utilizes a powerful language model to understand context, intent, and generate responses or actions.
   • Simple Memory: Maintains a conversational history, allowing the AI to remember previous interactions within a session.
   • HTTP Request Tool: Empowers the AI agent to make external HTTP requests, enabling it to fetch data, interact with APIs, or post information to other services.
   • MCP Client Tool: Provides a specialized tool for interacting with a Model Context Protocol (MCP) server, suggesting integration with a broader AI ecosystem or specific model services.
3. Edit Fields (Set): A "Set" node is included, which can be used to transform, filter, or map data within the workflow, potentially preparing data for the AI agent or processing its output.
4. Sticky Note: A sticky note is present, likely for documentation or temporary notes within the workflow design.
5. MCP Server Trigger: An additional trigger is defined for an MCP server, indicating that this workflow can also be part of a larger Model Context Protocol setup, potentially receiving instructions or data from another AI model or service.

Prerequisites/Requirements

To run this workflow, you will need:

• n8n Instance: A running instance of n8n.
• OpenAI API Key: For the "OpenAI Chat Model" node to access GPT-4o. This credential needs to be configured in n8n.
• LangChain Nodes: Ensure the @n8n/n8n-nodes-langchain package is installed in your n8n instance, as many nodes in this workflow belong to it.
• HTTP Request Tool Configuration: If the AI agent is intended to make HTTP requests, you will need to configure the necessary URLs, headers, and authentication for the "HTTP Request Tool".
• MCP Client/Server Configuration: If leveraging the Model Context Protocol, you will need to configure the "MCP Client Tool" and potentially the "MCP Server Trigger" with the appropriate endpoints and authentication for your MCP setup.

Setup/Usage

1. Import the Workflow: Download the provided JSON and import it into your n8n instance.
2. Configure Credentials:
   • Locate the "OpenAI Chat Model" node and configure your OpenAI API Key credential.
   • If using the HTTP Request Tool, ensure any necessary HTTP credentials are set up in n8n and linked to the tool.
   • If using the MCP Client Tool, configure the relevant MCP credentials.
3. Activate Triggers:
   • Enable the "When chat message received" trigger to start listening for incoming chat messages.
   • If you intend for this workflow to be triggered by an MCP server, ensure the "MCP Server Trigger" is also active and correctly configured to listen for incoming MCP requests.
4. Customize AI Agent:
   • Review the "AI Agent" node's configuration. You might want to adjust the prompt, temperature, or other parameters of the OpenAI Chat Model for optimal performance with your specific use case.
   • Examine the "HTTP Request Tool" and "MCP Client Tool" within the AI Agent to ensure they are configured to interact with your desired external services.
5. Test the Workflow: Run the workflow manually or send a test chat message to the configured trigger to observe its behavior and ensure it's functioning as expected.