Screen contact activity from CSV with MCP client and OpenAI gpt-4o-mini
Ready for 3.0What this workflow does
This AI workflow has 14 nodes and runs manually, when you click “Execute workflow”. Along the way it connects MCP Client and OpenAI.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Read CSV File (Read/Write Files from Disk): reads a file from disk
- Extract CSV Data (Extract from File): extracts data from a file
- Batch Process Contacts (Loop Over Items (Split in Batches)): loops over the items in batches
- Check Row Count Safety (Code): runs custom JavaScript code
- Generate MCP Steps Code (Code): runs custom JavaScript code
- Convert to CSV File (Convert to File): converts data to a file
- Perform MCP Calls (MCP Client): uses MCP Client
- Save CSV File (Read/Write Files from Disk): writes a file to disk
- Extract MCP Results (Code): runs custom JavaScript code
- Create Verdict Prompt (Code): runs custom JavaScript code
…plus 3 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (8)
- Manual Trigger
n8n-nodes-base.manualTrigger - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Extract from File
n8n-nodes-base.extractFromFile - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Code
n8n-nodes-base.code - Convert to File
n8n-nodes-base.convertToFile - MCP Client
@n8n/n8n-nodes-langchain.mcpClient - OpenAI
@n8n/n8n-nodes-langchain.openAi
From the author
Quick Overview This workflow manually processes a contacts CSV, fetches website/Facebook/Instagram page text via an MCP browser endpoint, then uses OpenAI to classify each contact as active, inactive, or uncertain and writes the results to an output CSV. How…