Phishing analysis - URLScan.io and VirusTotal
This n8n workflow automates the analysis of email messages received in a Microsoft Outlook inbox to identify indicators of compromise (IOCs), specifically suspicious URLs. It can be triggered manually or scheduled to run daily at midnight. The workflow begins by retrieving up to 100 read email messages from the Outlook inbox. However, there seems to be a configuration issue as it should retrieve unread messages, not read ones. It then marks these messages as read to avoid processing them again in the future. The messages are then split into individual items using the Split In Batches node for sequential processing. For each email, the workflow analyzes its content to find URLs, which are considered potential IOCs. If URLs are found, the workflow proceeds to check these URLs for potential threats using two services, URLScan.io and VirusTotal, in parallel. In the first path, URLScan.io scans each URL, and if there are no errors, the results from URLScan.io and VirusTotal are merged. If there are errors, the workflow waits 1 minute before attempting to retrieve the URLScan results again. The loop then continues for the next email. In the second path, VirusTotal is used to scan the URLs, and the results are retrieved. Finally, the workflow checks if the data field is not empty, filtering out items where no data was found. It then sends a summarized Slack message to report details about the analyzed email, including the subject, sender, date, URLScan report URL, and VirusTotal verdict for URLs that were reported as malicious. Potential issues during setup include configuring the Outlook node to retrieve unread messages, resolving a configuration issue in the VirusTotal node, and handling authentication and API keys for both URLScan.io and VirusTotal nodes. Additionally, proper error handling and testing with various email content types and URLs are essential to ensure the workflow accurately identifies IOCs and reports them to the Slack channel.
By n8n TeamGenerate Youtube video metadata (timestamps, tags, description, ...)
For Who? Content Creators Youtube Automation Marketing Team --- How it works? 1 - Enter the ID of the YTB channel to trigger the workflow when a new video is posted 2 - Apify scrape the last YTB video of the channel 3 - Wait until the dataset is completed in Apify and get it 4 - Verify if Metadata are not already generated and generate them with LLM 5 - Format all the data created and update YTB Video 📺 YouTube Video Tutorial: [](https://www.youtube.com/watch?v=HaQPAa6l5bU) --- SETUP Setup Input YTB Chanel : Go to the channel's page on YouTube, and look at the URL of the page. The channel ID is the value that comes after channel/ in the URL. Add it after "?channel_id=" You can also use free tools available to retrieve channel ID. Setup Output YTB Video Update : Connect your YTB account to your n8n instance thanks to the Google Cloud Console. You can find tutorials by typing "youtube api Oauth" on Google. APIs : For the following third-party integrations, replace ==[YOURAPITOKEN]== with your API Token or connect your account via Client ID / Secret to your n8n instance : Apify : https://docs.apify.com/api/v2/getting-started Youtube : https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.youtube/?utmsource=n8napp&utmmedium=nodesettingsmodal-credentiallink&utm_campaign=n8n-nodes-base.youTubetemplates-and-examples --- 👨💻 More Workflows : https://n8n.io/creators/nasser/
By NasserEasy image captioning with Gemini 1.5 Pro
This n8n workflow demonstrates how to automate image captioning tasks using Gemini 1.5 Pro - a multimodal LLM which can accept and analyse images. This is a really simple example of how easy it is to build and leverage powerful AI models in your repetitive tasks. How it works For this demo, we'll import a public image from a popular stock photography website, Pexel.com, into our workflow using the HTTP request node. With multimodal LLMs, there is little do preprocess other than ensuring the image dimensions fit within the LLMs accepted limits. Though not essential, we'll resize the image using the Edit image node to achieve fast processing. The image is used as an input to the basic LLM node by defining a "user message" entry with the binary (data) type. The LLM node has the Gemini 1.5 Pro language model attached and we'll prompt it to generate a caption title and text appropriate for the image it sees. Once generated, the generated caption text is positioning over the original image to complete the task. We can calculate the positioning relative to the amount of characters produced using the code node. An example of the combined image and caption can be found here: https://res.cloudinary.com/daglih2g8/image/upload/fauto,qauto/v1/n8n-workflows/l5xbb4ze4wyxwwefqmnc Requirements Google Gemini API Key. Access to Google Drive. Customising the workflow Not using Google Gemini? n8n's basic LLM node supports the standard syntax for image content for models that support it - try using GPT4o, Claude or LLava (via Ollama). Google Drive is only used for demonstration purposes. Feel free to swap this out for other triggers such as webhooks to fit your use case.
By JimleukWordPress - AI chatbot to enhance user experience - with Supabase and OpenAI
This is the first version of a template for a RAG/GenAI App using WordPress content. As creating, sharing, and improving templates brings me joy 😄, feel free to reach out on LinkedIn if you have any ideas to enhance this template! How It Works This template includes three workflows: Workflow 1: Generate embeddings for your WordPress posts and pages, then store them in the Supabase vector store. Workflow 2: Handle upserts for WordPress content when edits are made. Workflow 3: Enable chat functionality by performing Retrieval-Augmented Generation (RAG) on the embedded documents. Why use this template? This template can be applied to various use cases: Build a GenAI application that requires embedded documents from your website's content. Embed or create a chatbot page on your website to enhance user experience as visitors search for information. Gain insights into the types of questions visitors are asking on your website. Simplify content management by asking the AI for related content ideas or checking if similar content already exists. Useful for internal linking. Prerequisites Access to Supabase for storing embeddings. Basic knowledge of Postgres and pgvector. A WordPress website with content to be embedded. An OpenAI API key Ensure that your n8n workflow, Supabase instance, and WordPress website are set to the same timezone (or use GMT) for consistency. Workflow 1 : Initial Embedding This workflow retrieves your WordPress pages and posts, generates embeddings from the content, and stores them in Supabase using pgvector. Step 0 : Create Supabase tables Nodes : Postgres - Create Documents Table: This table is structured to support OpenAI embedding models with 1536 dimensions Postgres - Create Workflow Execution History Table These two nodes create tables in Supabase: The documents table, which stores embeddings of your website content. The n8nwebsiteembedding_histories table, which logs workflow executions for efficient management of upserts. This table tracks the workflow execution ID and execution timestamp. Step 1 : Retrieve and Merge WordPress Pages and Posts Nodes : WordPress - Get All Posts WordPress - Get All Pages Merge WordPress Posts and Pages These three nodes retrieve all content and metadata from your posts and pages and merge them. Important: Apply filters to avoid generating embeddings for all site content. Step 2 : Set Fields, Apply Filter, and Transform HTML to Markdown Nodes : Set Fields Filter - Only Published & Unprotected Content HTML to Markdown These three nodes prepare the content for embedding by: Setting up the necessary fields for content embeddings and document metadata. Filtering to include only published and unprotected content (protected=false), ensuring private or unpublished content is excluded from your GenAI application. Converting HTML to Markdown, which enhances performance and relevance in Retrieval-Augmented Generation (RAG) by optimizing document embeddings. Step 3: Generate Embeddings, Store Documents in Supabase, and Log Workflow Execution Nodes: Supabase Vector Store Sub-nodes: Embeddings OpenAI Default Data Loader Token Splitter Aggregate Supabase - Store Workflow Execution This step involves generating embeddings for the content and storing it in Supabase, followed by logging the workflow execution details. Generate Embeddings: The Embeddings OpenAI node generates vector embeddings for the content. Load Data: The Default Data Loader prepares the content for embedding storage. The metadata stored includes the content title, publication date, modification date, URL, and ID, which is essential for managing upserts. ⚠️ Important Note : Be cautious not to store any sensitive information in metadata fields, as this information will be accessible to the AI and may appear in user-facing answers. Token Management: The Token Splitter ensures that content is segmented into manageable sizes to comply with token limits. Aggregate: Ensure the last node is run only for 1 item. Store Execution Details: The Supabase - Store Workflow Execution node saves the workflow execution ID and timestamp, enabling tracking of when each content update was processed. This setup ensures that content embeddings are stored in Supabase for use in downstream applications, while workflow execution details are logged for consistency and version tracking. This workflow should be executed only once for the initial embedding. Workflow 2, described below, will handle all future upserts, ensuring that new or updated content is embedded as needed. Workflow 2: Handle document upserts Content on a website follows a lifecycle—it may be updated, new content might be added, or, at times, content may be deleted. In this first version of the template, the upsert workflow manages: Newly added content Updated content Step 1: Retrieve WordPress Content with Regular CRON Nodes: CRON - Every 30 Seconds Postgres - Get Last Workflow Execution WordPress - Get Posts Modified After Last Workflow Execution WordPress - Get Pages Modified After Last Workflow Execution Merge Retrieved WordPress Posts and Pages A CRON job (set to run every 30 seconds in this template, but you can adjust it as needed) initiates the workflow. A Postgres SQL query on the n8nwebsiteembedding_histories table retrieves the timestamp of the latest workflow execution. Next, the HTTP nodes use the WordPress API (update the example URL in the template with your own website’s URL and add your WordPress credentials) to request all posts and pages modified after the last workflow execution date. This process captures both newly added and recently updated content. The retrieved content is then merged for further processing. Step 2 : Set fields, use filter Nodes : Set fields2 Filter - Only published and unprotected content The same that Step 2 in Workflow 1, except that HTML To Makrdown is used in further Step. Step 3: Loop Over Items to Identify and Route Updated vs. Newly Added Content Here, I initially aimed to use 'update documents' instead of the delete + insert approach, but encountered challenges, especially with updating both content and metadata columns together. Any help or suggestions are welcome! :) Nodes: Loop Over Items Postgres - Filter on Existing Documents Switch Route existing_documents (if documents with matching IDs are found in metadata): Supabase - Delete Row if Document Exists: Removes any existing entry for the document, preparing for an update. Aggregate2: Used to aggregate documents on Supabase with ID to ensure that Set Fields3 is executed only once for each WordPress content to avoid duplicate execution. Set Fields3: Sets fields required for embedding updates. Route new_documents (if no matching documents are found with IDs in metadata): Set Fields4: Configures fields for embedding newly added content. In this step, a loop processes each item, directing it based on whether the document already exists. The Aggregate2 node acts as a control to ensure Set Fields3 runs only once per WordPress content, effectively avoiding duplicate execution and optimizing the update process. Step 4 : HTML to Markdown, Supabase Vector Store, Update Workflow Execution Table The HTML to Markdown node mirrors Workflow 1 - Step 2. Refer to that section for a detailed explanation on how HTML content is converted to Markdown for improved embedding performance and relevance. Following this, the content is stored in the Supabase vector store to manage embeddings efficiently. Lastly, the workflow execution table is updated. These nodes mirros the Workflow 1 - Step 3 nodes. Workflow 3 : An example of GenAI App with Wordpress Content : Chatbot to be embed on your website Step 1: Retrieve Supabase Documents, Aggregate, and Set Fields After a Chat Input Nodes: When Chat Message Received Supabase - Retrieve Documents from Chat Input Embeddings OpenAI1 Aggregate Documents Set Fields When a user sends a message to the chat, the prompt (user question) is sent to the Supabase vector store retriever. The RPC function match_documents (created in Workflow 1 - Step 0) retrieves documents relevant to the user’s question, enabling a more accurate and relevant response. In this step: The Supabase vector store retriever fetches documents that match the user’s question, including metadata. The Aggregate Documents node consolidates the retrieved data. Finally, Set Fields organizes the data to create a more readable input for the AI agent. Directly using the AI agent without these nodes would prevent metadata from being sent to the language model (LLM), but metadata is essential for enhancing the context and accuracy of the AI’s response. By including metadata, the AI’s answers can reference relevant document details, making the interaction more informative. Step 2: Call AI Agent, Respond to User, and Store Chat Conversation History Nodes: AI Agent Sub-nodes: OpenAI Chat Model Postgres Chat Memories Respond to Webhook This step involves calling the AI agent to generate an answer, responding to the user, and storing the conversation history. The model used is gpt4-o-mini, chosen for its cost-efficiency.
By DatakiVoiceflow demo support chatbot
Submission Overview for Voiceflow Demo Workflow View the YouTube video for this workflow here. Who is this for? This workflow is ideal for businesses and developers using Voiceflow to power AI voice chatbots. It benefits teams that want to enhance chatbot functionality through integrations with platforms like Zendesk, Google Calendar, and Airtable. What problem is this workflow solving? The workflow addresses the need for seamless integration of chatbot interactions with backend systems. It automates customer service tasks such as ticket creation, meeting scheduling, and data reporting, reducing manual effort and enhancing efficiency. What does this workflow do? Customer Lookup: Checks the database for existing customers and returns relevant details or a "NOT_FOUND" status. Zendesk Ticket Creation: Automates the creation of support tickets for customer issues. Meeting Scheduling: Integrates with Google Calendar to provide availability and schedule meetings. Transcript Reporting: Aggregates interaction data and sends it to Airtable for analysis by the product team. Setup Configure your Voiceflow chatbot to connect to this workflow via a webhook. Set up the required integrations: Zendesk API: For ticket creation. Google Calendar API: For scheduling. Airtable API: For storing transcripts. Customize the workflow's nodes to match your use case, such as database fields or API endpoints. Deploy the workflow on your n8n instance and test the integrations. How to customize this workflow to your needs Adjust database queries to match your customer data schema. Modify the Zendesk ticket payload to include additional fields or custom formats. Update Google Calendar configurations for different scheduling requirements. Add or remove Airtable fields based on the product team's analysis needs. This template adheres to n8n’s submission guidelines, ensuring clarity, relevance, and broad applicability for users in customer service, product development, and automation.
By Angel MenendezNathan: Your n8n personal assistant
Nathan is a proof of concept framework for creating a personal assistant who can handle various day to day functions for you.
By jasonBuild your own PostgreSQL MCP server
This n8n demonstrates how to build a simple PostgreSQL MCP server to manage your PostgreSQL database such as HR, Payroll, Sale, Inventory and More! This MCP example is based off an official MCP reference implementation which can be found here -https://github.com/modelcontextprotocol/servers/tree/main/src/postgres How it works A MCP server trigger is used and connected to 5 tools: 2 postgreSQL and 3 custom workflow. The 2 postgreSQL tools are simple read-only queries and as such, the postgreSQL tool can be simply used. The 3 custom workflow tools are used for select, insert and update queries as these are operations which require a bit more discretion. Whilst it may be easier to allow the agent to use raw SQL queries, we may find it a little safer to just allow for the parameters instead. The custom workflow tool allows us to define this restricted schema for tool input which we'll use to construct the SQL statement ourselves. All 3 custom workflow tools trigger the same "Execute workflow" trigger in this very template which has a switch to route the operation to the correct handler. Finally, we use our standard PostgreSQL node to handle select, insert and update operations. The responses are then sent back to the the MCP client. How to use This PostgreSQL MCP server allows any compatible MCP client to manage a PostgreSQL database by supporting select, create and update operations. You will need to have a database available before you can use this server. Connect your MCP client by following the n8n guidelines here - https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger/integrating-with-claude-desktop Try the following queries in your MCP client: "Please help me check if Alex has an entry in the users table. If not, please help me create a record for her." "What was the top selling product in the last week?" "How many high priority support tickets are still open this morning?" Requirements PostgreSQL for database. This can be an external database such as Supabase or one you can host internally. MCP Client or Agent for usage such as Claude Desktop - https://claude.ai/download Customising this workflow If the scope of schemas or tables is too open, try restrict it so the MCP serves a specific purpose for business operations. eg. Confine the querying and editing to HR only tables before providing access to people in that department. Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!
By JimleukGenerate and insert data into a Postgres database
This is Workflow 1 in the blog tutorial Database activity monitoring and alerting. Prerequisites A Postgres database set up and credentials. Basic knowledge of JavaScript and SQL. Nodes Cron node starts the workflow every minute. Function node generates sensor data (sensor id (preset), a randomly generated value, timestamp, and notification (preset as false) ) Postgres node inserts the data into a Postgres database. You can create the database for this workflow with the following SQL statement: SQL CREATE TABLE n8n (id SERIAL, sensorid VARCHAR, value INT, timestamp TIMESTAMP, notification BOOLEAN);
By tanaypantWrite JSON to disk (binary)
The “Write Binary File” expects binary data. The JSON data is, however, JSON ;) There should really be a node that allows moving data around between both of them. For now, it can be done with a Function-Node. At least till a proper one is in place. The first node is example data, wich you can customize or replace. The second node named “Make Binary” is the important one with the custom code which makes the data binary and writes it to the correct location.
By mikeDomain extractor
This node is designed to cleanse URLs and extract their domain names efficiently. It effectively handles a wide range of URL formats, including those with unconventional or complex top-level domains (TLDs), such as 'co.uk'. You can also use it to extract the domain from an email. The node will also check if the domain is from a free email provider (gmail.com / outlook.com...etc) or not. How It Works The node analyzes the provided URL, removing any unnecessary elements. It then identifies and extracts the domain name, ensuring compatibility with a diverse array of TLDs. The node utilizes an extensive list of TLDs to guarantee accurate domain extraction for virtually any URL. To view the complete list of supported top-level domains, please visit: TLD List on GitHub How to use it Call this workflow using the "execute workflow" node You can pass either an email variable or a url variable. For email, the node also detect free mail provider such as Yahoo / Google...etc
By Lucas PerretCreate multiple JSON items from an array
You can use the Function node to create multiple JSON items from an array.
By Harshil AgrawalConvert RSS news to AI avatar videos with Heygen & GPT-4o
🎬 Automated News-to-Video Workflow (n8n + Heygen + GPT-4o) 📄 Overview: This n8n workflow turns news from an RSS feed (e.g., CNN) into short, AI-generated avatar videos using Heygen. It: Fetches news from an RSS feed. Logs headlines to Google Sheets. Uses GPT-4o or Google Gemini to generate a 30–60 sec script. Sends the script to Heygen to create an avatar video. Monitors and retrieves the final video. Logs video metadata (title, link, etc.) to Google Sheets. 🎯 Ideal for content creators, marketers, or media pages repurposing written news into video content at scale. --- ⚙️ Setup Guide (No Sensitive Info) 🔑 1. Heygen API Paid Heygen plan required. Add your API key in the Setup Heygen node: json "heygenapikey": "yourkeyhere" Optional: Set "avatarid" and "voiceid" as desired. 💡 2. AI Model: GPT-4o or Gemini GPT-4o: Use OpenAI’s node or HTTP request with your API key. Gemini: Link your Google Cloud project and connect the Gemini node using OAuth2 credentials. 📥 3. RSS Feed Add an RSS node (e.g., CNN). Extract title, link, and content. 📊 4. Google Sheets + Drive Connect via OAuth2: "Google Sheets account 2" "Google Drive account 2" Replace sheet IDs in: Log news to sheets Log video URL and title to sheets 📹 5. Create Video (Heygen) Send a POST request to Heygen's API using the generated script, avatar, and voice ID. ⏳ 6. Monitor Status Poll the status endpoint until video is ready. Capture the download link. 🧾 7. Log Final Output Save video metadata to a Google Sheet for publishing or archiving. Set up video: Link in Workflow ---
By David Olusola