Transform uploaded documents into structured data with Unstructured MCP
Ready for 3.0What this workflow does
This AI workflow has 16 nodes and runs when someone submits an n8n form (“Document”). Along the way it connects MCP Client.
How it runs
Trigger: When someone submits an n8n form (“Document”).
- If: checks a condition and branches into true / false
- Fetch Upload URL (MCP Client): uses MCP Client
- Notify File Too Large (n8n Form): shows the next form page
- Append File to Upload Request (Code): runs custom JavaScript code
- Upload File to URL (HTTP Request): calls an HTTP API (PUT)
- Initiate File Transformation (MCP Client): uses MCP Client
- Check Transformation Status (MCP Client): uses MCP Client
- Route by Job Status (Switch): routes items into 3 branches
- Fetch Transformation Results (MCP Client): uses MCP Client
- Wait: pauses before continuing
…plus 5 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 (10)
- n8n Form Trigger
n8n-nodes-base.formTrigger - If
n8n-nodes-base.if - MCP Client
@n8n/n8n-nodes-langchain.mcpClient - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Switch
n8n-nodes-base.switch - Edit Fields (Set)
n8n-nodes-base.set - Wait
n8n-nodes-base.wait - Stop and Error
n8n-nodes-base.stopAndError - n8n Form
n8n-nodes-base.form
From the author
Quick overview This workflow collects an uploaded document via an n8n form and uses Unstructured’s hosted Transform MCP server to convert it into structured, LLM-ready text output, then returns the extracted content and basic stats (elements, characters)…