Build your own Youtube MCP server
Ready for 3.0What this workflow does
This AI workflow has 15 nodes and runs when an MCP client calls one of its tools (plus 1 other trigger). It uses only n8n's built-in nodes. It also calls api.apify.com over HTTP.
How it runs
Trigger: When an MCP client calls one of its tools (plus 1 other trigger).
- Operation (Switch): routes items into 3 branches
- Apify Youtube Search (HTTP Request): calls api.apify.com
- Apify Youtube Transcripts (HTTP Request): calls api.apify.com
- Get Usage Metrics (HTTP Request): calls api.apify.com
- Simplify Search Results (Edit Fields (Set)): sets 6 fields: channelName, title, url…
- Simplify Transcript Results (Edit Fields (Set)): sets 3 fields: title, url, transcript
- Get Usage Limits (HTTP Request): calls api.apify.com
- Aggregate: combines items into one
- Aggregate: combines items into one
- Simplify Usage Metrics (Edit Fields (Set)): sets 15 fields: monthlyUsageCycle_startAt, monthlyUsageCycle_endAt, monthlyUsageUsd…
HTTP calls to: api.apify.com
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 (7)
- Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Switch
n8n-nodes-base.switch - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - Aggregate
n8n-nodes-base.aggregate - MCP Server Trigger
@n8n/n8n-nodes-langchain.mcpTrigger
From the author
This n8n demonstrates how to build a simple Youtube MCP server to look up videos on Youtube and download their transcripts for research purposes. Youtube videos are a great source of new and updated information on a variety of cutting edge developments but…