The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "ATDF + MCP Integration Comparison",
"nodes": [
{
"parameters": {},
"id": "webhook-trigger",
"name": "Webhook Trigger",
"type": "n8n-nodes-base.webhook",
"typeVersion": 1,
"position": [
240,
300
]
},
{
"parameters": {
"serverUrl": "http://localhost:8001/sse",
"operation": "listTools"
},
"id": "mcp-native-list",
"name": "MCP Native - List Tools",
"type": "n8n-nodes-base.mcpClient",
"typeVersion": 1,
"position": [
460,
200
]
},
{
"parameters": {
"operation": "listTools",
"language": "es",
"includeMetadata": true,
"includeSchemas": true
},
"id": "atdf-mcp-list",
"name": "ATDF-MCP - List Tools",
"type": "n8n-nodes-atdf-mcp.atdfMcpClient",
"typeVersion": 1,
"position": [
460,
400
]
},
{
"parameters": {
"serverUrl": "http://localhost:8001/sse",
"operation": "callTool",
"toolName": "calculate_metrics",
"arguments": {
"data": "={{ $json.data }}",
"format": "json"
}
},
"id": "mcp-native-execute",
"name": "MCP Native - Execute",
"type": "n8n-nodes-base.mcpClient",
"typeVersion": 1,
"position": [
680,
200
]
},
{
"parameters": {
"operation": "executeTool",
"toolName": "calculate_metrics",
"parameters": {
"data": "={{ $json.data }}",
"format": "json",
"locale": "es-ES"
},
"language": "es",
"validateSchema": true,
"includeMetadata": true
},
"id": "atdf-mcp-execute",
"name": "ATDF-MCP - Execute",
"type": "n8n-nodes-atdf-mcp.atdfMcpClient",
"typeVersion": 1,
"position": [
680,
400
]
},
{
"parameters": {
"jsCode": "// Comparar resultados de ambos enfoques\nconst mcpResult = $input.first();\nconst atdfResult = $input.last();\n\nreturn {\n comparison: {\n mcp_native: {\n tools_count: mcpResult.tools?.length || 0,\n has_metadata: !!mcpResult.metadata,\n localized: false\n },\n atdf_mcp: {\n tools_count: atdfResult.tools?.length || 0,\n has_metadata: !!atdfResult.metadata,\n localized: !!atdfResult.localization,\n schemas_included: !!atdfResult.schemas\n },\n recommendation: atdfResult.tools?.length > mcpResult.tools?.length ? \n 'ATDF-MCP provides richer metadata' : \n 'Both approaches work similarly'\n }\n};"
},
"id": "compare-results",
"name": "Compare Results",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
300
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ $json }}"
},
"id": "response",
"name": "Response",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
1120,
300
]
}
],
"connections": {
"Webhook Trigger": {
"main": [
[
{
"node": "MCP Native - List Tools",
"type": "main",
"index": 0
},
{
"node": "ATDF-MCP - List Tools",
"type": "main",
"index": 0
}
]
]
},
"MCP Native - List Tools": {
"main": [
[
{
"node": "MCP Native - Execute",
"type": "main",
"index": 0
}
]
]
},
"ATDF-MCP - List Tools": {
"main": [
[
{
"node": "ATDF-MCP - Execute",
"type": "main",
"index": 0
}
]
]
},
"MCP Native - Execute": {
"main": [
[
{
"node": "Compare Results",
"type": "main",
"index": 0
}
]
]
},
"ATDF-MCP - Execute": {
"main": [
[
{
"node": "Compare Results",
"type": "main",
"index": 0
}
]
]
},
"Compare Results": {
"main": [
[
{
"node": "Response",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"staticData": null,
"tags": [],
"triggerCount": 0,
"updatedAt": "2024-01-20T10:00:00.000Z",
"versionId": "1"
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
ATDF + MCP Integration Comparison. Uses mcpClient, n8n-nodes-atdf-mcp. Webhook trigger; 7 nodes.
Source: https://github.com/MauricioPerera/agent-tool-description-format/blob/c762a6cc3239cd3f0bde6338f46bc197a8c80474/examples/n8n_mcp_comparison_workflow.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Jigsaw API key for image processing, I use this as a gatekeeper/second pair of eyes. LINK to their website https://jigsawstack.com/ SECOND A postgress DATABASE (I use Supabase) LlamaCloud for the pars
Whatsapp Multi Agent System optimized copy 2.0. Uses airtable, httpRequest, errorTrigger. Webhook trigger; 44 nodes.
Invoice Agent. Uses httpRequest, emailSend. Webhook trigger; 29 nodes.
Reputation Engine — SEO QA Agent. Uses httpRequest. Webhook trigger; 28 nodes.
This workflow handles incoming voice calls or audio messages, transcribes them using Whisper (OpenAI) or ElevenLabs, extracts booking intent and preferred time slots using AI, checks availability on C