Construire un serveur MCP Google Drive personnalisé
Avancé
Ceci est unBuilding Blocks, AIworkflow d'automatisation du domainecontenant 17 nœuds.Utilise principalement des nœuds comme Set, Switch, GoogleDrive, ExtractFromFile, GoogleDriveTool, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Construire un serveur MCP personnalisé pour Google Drive
Prérequis
- •Informations d'identification Google Drive API
- •Clé API OpenAI
Nœuds utilisés (17)
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
"meta": {
"instanceId": "408f9fb9940c3cb18ffdef0e0150fe342d6e655c3a9fac21f0f644e8bedabcd9",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "fb5b682b-5e30-497e-b465-c3369bb3c2e3",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-32,
-20
],
"parameters": {
"color": 7,
"width": 680,
"height": 660,
"content": "## 1. Set up an MCP Server Trigger\n[Read more about the MCP Server Trigger](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger)"
},
"typeVersion": 1
},
{
"id": "cfc2c7f1-a6ee-42a9-b955-e5bce012b6e1",
"name": "Note adhésive 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-40,
-160
],
"parameters": {
"color": 5,
"width": 380,
"height": 100,
"content": "### Always Authenticate Your Server!\nBefore going to production, it's always advised to enable authentication on your MCP server trigger."
},
"typeVersion": 1
},
{
"id": "79586d35-0582-4da8-91da-5bc8451c2089",
"name": "Lorsqu'exécuté par un autre workflow",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
800,
360
],
"parameters": {
"workflowInputs": {
"values": [
{
"name": "operation"
},
{
"name": "folderId"
},
{
"name": "fileId"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "02aee033-58e8-4f33-a18d-b872840e81d8",
"name": "Google Drive MCP Server",
"type": "@n8n/n8n-nodes-langchain.mcpTrigger",
"position": [
160,
160
],
"webhookId": "a289c719-fb71-4b08-97c6-79d12645dc7e",
"parameters": {
"path": "a289c719-fb71-4b08-97c6-79d12645dc7e"
},
"typeVersion": 1
},
{
"id": "e0e50653-d98a-4ad4-a2ed-e1b73332c380",
"name": "Note adhésive 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
680,
-20
],
"parameters": {
"color": 7,
"width": 1340,
"height": 860,
"content": "## 2. Handle Multiple Binary Formats via Conversion and AI\n[Read more about the PostgreSQL Node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.postgres/)\n\nMCP clients (or rather, the AI agents) still expect and require text responses from our MCP server.\nN8N can provide the right conversion tools to parse most text formats such as PDF, CSV and XML.\nFor images, audio and video, consider using multimodal LLMs to describe or transcribe the file instead."
},
"typeVersion": 1
},
{
"id": "6be1ff49-5edc-42d2-87de-09d207ee7733",
"name": "Télécharger le fichier 1",
"type": "n8n-nodes-base.googleDrive",
"position": [
1160,
360
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.fileId }}"
},
"options": {
"googleFileConversion": {
"conversion": {
"docsToFormat": "text/plain",
"slidesToFormat": "application/pdf"
}
}
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "yOwz41gMQclOadgu",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "91b0a549-0494-48a1-bdf3-6c2b91409d01",
"name": "FileType",
"type": "n8n-nodes-base.switch",
"position": [
1340,
320
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "pdf",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "7b6958ce-d553-4379-a5d6-743f39b342d0",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $binary.data.mimeType }}",
"rightValue": "application/pdf"
}
]
},
"renameOutput": true
},
{
"outputKey": "csv",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "d0816a37-ac06-49e3-8d63-17fcd061e33f",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $binary.data.mimeType }}",
"rightValue": "text/csv"
}
]
},
"renameOutput": true
},
{
"outputKey": "image",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "589540e1-1439-41e3-ba89-b27f5e936190",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{\n[\n 'image/jpeg',\n 'image/jpg',\n 'image/png',\n 'image/gif'\n].some(mimeType => $binary.data.mimeType === mimeType)\n}}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "audio",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b8fc61a1-6057-4db3-960e-b8ddcbdd0f31",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $binary.data.mimeType }}",
"rightValue": "audio"
}
]
},
"renameOutput": true
},
{
"outputKey": "video",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "959d65a6-372f-4978-b2d1-f28aa1e372c6",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $binary.data.mimeType }}",
"rightValue": "video"
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "d88ed202-1121-41db-859d-b31d53d46292",
"name": "Operation",
"type": "n8n-nodes-base.switch",
"position": [
980,
360
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "ReadFile",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b03bb746-dc4e-469c-b8e6-a34c0aa8d0a6",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.operation }}",
"rightValue": "readFile"
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "7e8791e6-24c2-441a-8efb-7f4375f2519b",
"name": "Extraire du PDF",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1620,
80
],
"parameters": {
"options": {},
"operation": "pdf"
},
"typeVersion": 1
},
{
"id": "2b33623c-cea4-4a83-80ef-f852b9a3d126",
"name": "Extraire de CSV",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1620,
260
],
"parameters": {
"options": {
"encoding": "utf-8",
"headerRow": false,
"relaxQuotes": true,
"includeEmptyCells": true
}
},
"typeVersion": 1
},
{
"id": "6ca2542d-225e-4a65-b5ce-3edafb11379c",
"name": "Obtenir la réponse PDF",
"type": "n8n-nodes-base.set",
"position": [
1780,
80
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "a481cde3-b8ec-4d97-aa13-4668bd66c24d",
"name": "response",
"type": "string",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "3d1c4aa6-cac1-4957-ab7e-3134368e4b53",
"name": "Obtenir la réponse CSV",
"type": "n8n-nodes-base.set",
"position": [
1780,
260
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "a481cde3-b8ec-4d97-aa13-4668bd66c24d",
"name": "response",
"type": "string",
"value": "={{\n$input.all()\n .map(item => item.json.row.map(cell => `\"${cell}\"`).join(','))\n .join('\\n')\n}}"
}
]
}
},
"executeOnce": true,
"typeVersion": 3.4
},
{
"id": "141444f9-e937-41f9-ab97-09624646ddba",
"name": "Lire le fichier depuis GDrive",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
400,
380
],
"parameters": {
"name": "ReadFile",
"workflowId": {
"__rl": true,
"mode": "id",
"value": "={{ $workflow.id }}"
},
"description": "Call this tool to download and read the contents of a file within google drive.",
"workflowInputs": {
"value": {
"fileId": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('fileId', ``, 'string') }}",
"folderId": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('folderId', ``, 'string') }}",
"operation": "readFile"
},
"schema": [
{
"id": "operation",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "operation",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "folderId",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "folderId",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "fileId",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "fileId",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"typeVersion": 2.1
},
{
"id": "b5851527-0b57-447b-ac8c-10408a684862",
"name": "Rechercher des fichiers depuis GDrive",
"type": "n8n-nodes-base.googleDriveTool",
"position": [
240,
380
],
"parameters": {
"limit": 10,
"filter": {
"driveId": {
"mode": "list",
"value": "My Drive"
},
"whatToSearch": "files"
},
"options": {},
"resource": "fileFolder",
"queryString": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Search_Query', ``, 'string') }}"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "yOwz41gMQclOadgu",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "98197c91-c7e9-4fbb-a2b1-c16c873fa0a1",
"name": "Analyser l'image",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
1620,
440
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4O-MINI"
},
"options": {},
"resource": "image",
"inputType": "base64",
"operation": "analyze"
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1.8
},
{
"id": "b44a787a-c670-47e1-b87e-d880425ce610",
"name": "Transcrire l'audio",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
1620,
620
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "transcribe"
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1.8
},
{
"id": "1e1a358d-769e-48c9-bf27-6a3cfaaacb14",
"name": "Note adhésive 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-500,
-420
],
"parameters": {
"width": 440,
"height": 1060,
"content": "## Try It Out!\n### This n8n demonstrates how to build a simple Google Drive MCP server to search and get contents of files from Google Drive.\n\nThis MCP example is based off an official MCP reference implementation which can be found here -https://github.com/modelcontextprotocol/servers/tree/main/src/gdrive\n\n### How it works\n* A MCP server trigger is used and connected to 1x Google Drive tool and 1x Custom Workflow tool.\n* The Google Drive tool is set to perform a search on files within our Google Drive folder.\n* The Custom Workflow tool downloads target files found in our drive and converts the binaries to their text representation. Eg. PDFs have only their text contents extracted and returned to the MCP client.\n\n### How to use\n* This Google Drive MCP server allows any compatible MCP client to manage a person or shared Google Drive. Simple select a drive or for better control, specify a folder within the drive to scope the operations to.\n* 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\n* Try the following queries in your MCP client:\n * \"Please help me search for last month's expense reports.\"\n * \"What does the company policy document say about cancellations and refunds?\"\n\n### Requirements\n* Google Drive for documents.\n* OpenAI for image and audio understanding.\n* MCP Client or Agent for usage such as Claude Desktop - https://claude.ai/download\n\n### Customising this workflow\n* Add additional capabilities such as renaming, moving and/or deleting files.\n* Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"91b0a549-0494-48a1-bdf3-6c2b91409d01": {
"main": [
[
{
"node": "7e8791e6-24c2-441a-8efb-7f4375f2519b",
"type": "main",
"index": 0
}
],
[
{
"node": "2b33623c-cea4-4a83-80ef-f852b9a3d126",
"type": "main",
"index": 0
}
],
[
{
"node": "98197c91-c7e9-4fbb-a2b1-c16c873fa0a1",
"type": "main",
"index": 0
}
],
[
{
"node": "b44a787a-c670-47e1-b87e-d880425ce610",
"type": "main",
"index": 0
}
],
[]
]
},
"d88ed202-1121-41db-859d-b31d53d46292": {
"main": [
[
{
"node": "6be1ff49-5edc-42d2-87de-09d207ee7733",
"type": "main",
"index": 0
}
]
]
},
"6be1ff49-5edc-42d2-87de-09d207ee7733": {
"main": [
[
{
"node": "91b0a549-0494-48a1-bdf3-6c2b91409d01",
"type": "main",
"index": 0
}
]
]
},
"2b33623c-cea4-4a83-80ef-f852b9a3d126": {
"main": [
[
{
"node": "3d1c4aa6-cac1-4957-ab7e-3134368e4b53",
"type": "main",
"index": 0
}
]
]
},
"7e8791e6-24c2-441a-8efb-7f4375f2519b": {
"main": [
[
{
"node": "6ca2542d-225e-4a65-b5ce-3edafb11379c",
"type": "main",
"index": 0
}
]
]
},
"141444f9-e937-41f9-ab97-09624646ddba": {
"ai_tool": [
[
{
"node": "02aee033-58e8-4f33-a18d-b872840e81d8",
"type": "ai_tool",
"index": 0
}
]
]
},
"b5851527-0b57-447b-ac8c-10408a684862": {
"ai_tool": [
[
{
"node": "02aee033-58e8-4f33-a18d-b872840e81d8",
"type": "ai_tool",
"index": 0
}
]
]
},
"79586d35-0582-4da8-91da-5bc8451c2089": {
"main": [
[
{
"node": "d88ed202-1121-41db-859d-b31d53d46292",
"type": "main",
"index": 0
}
]
]
}
}
}Foire aux questions
Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Avancé - Blocs de construction, Intelligence Artificielle
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Construire un serveur MCP YouTube personnalisé
Construire un serveur MCP personnalisé pour YouTube
Set
Switch
Aggregate
+
Set
Switch
Aggregate
20 NœudsJimleuk
Blocs de construction
Construire un serveur MCP API personnalisé
Construire un serveur MCP personnalisé pour API
If
Set
Filter
+
If
Set
Filter
25 NœudsJimleuk
Ingénierie
Construire un serveur MCP GitHub personnalisé
Construire un serveur MCP personnalisé pour GitHub
Set
Github
Switch
+
Set
Github
Switch
19 NœudsJimleuk
Ingénierie
Construire un serveur MCP de stockage vectoriel Qdrant personnalisé
Construire un serveur MCP personnalisé pour le stockage de vecteurs Qdrant
If
Set
Code
+
If
Set
Code
44 NœudsJimleuk
Blocs de construction
Construire un assistant juridique fiscal avec Qdrant, Mistral.ai et OpenAI
Construire un assistant en matière de fiscalité avec Qdrant, Mistral.ai et OpenAI
Set
Wait
Filter
+
Set
Wait
Filter
38 NœudsJimleuk
Finance
Construire un assistant de connaissances multi-sources intégrant Claude, RAG, Perplexity et Drive
Construire un assistant de connaissances multi-sources intégrant Claude, RAG, Perplexity et Drive
Set
Switch
Google Drive
+
Set
Switch
Google Drive
38 NœudsPaul
Wiki interne
Informations sur le workflow
Niveau de difficulté
Avancé
Nombre de nœuds17
Catégorie2
Types de nœuds10
Description de la difficulté
Auteur
Jimleuk
@jimleukFreelance consultant based in the UK specialising in AI-powered automations. I work with select clients tackling their most challenging projects. For business enquiries, send me an email at hello@jimle.uk LinkedIn: https://www.linkedin.com/in/jimleuk/ X/Twitter: https://x.com/jimle_uk
Liens externes
Voir sur n8n.io →
Partager ce workflow