Bear Brown
← All N8N workflows
AI & researchAggregateCodeDocument Default Data LoaderEmbeddings Open AiExecute Workflow Trigger

Prerequisite: Setup Qdrant Collection

Configured with Aggregate, Document Default Data Loader, Embeddings Open Ai, Execute Workflow Trigger, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSONView files on GitHub ↗37 nodes · MIT
Workflow preview
SubworkflowInsertTool WorkflowSubworkflowSearchTool WorkflowSubworkflowRecommendTool WorkflowTriggerQdrant MCP ServerMcp TriggerTriggerWhen Executed byAnother WorkflowExecute Workflow TriggerRoutingOperationSwitchSubworkflowCompareTool WorkflowWeb / APIRecommend APIHTTP RequestWeb / APIGet EmbeddingsHTTP RequestCodePreferences to ItemsCodeTransformAggregate EmbeddingsAggregateWeb / APIGet Embeddings1HTTP RequestTransformAggregate Embeddings1AggregateWeb / APIGroup Search APIHTTP RequestRoutingHas Results?IfTransformSimplify Group ResultsEdit FieldsTransformEmpty Compare ResponseEdit FieldsTransformAggregate CompareResponseAggregateAI & modelsEmbeddings OpenAIEmbeddings Open AiFiles / mediaDefault Data LoaderDocument Default Data Lo…TransformRecursive CharacterText SplitterText Splitter Recursive …TransformSimplify RecommendResponseEdit FieldsTransformGet Insert ResponseEdit FieldsTransformGet Search ResponseAggregateData storeInsert ReviewsVector Store QdrantData storeSearch ReviewsVector Store QdrantTransformSplit Out CompaniesSplit OutRoutingFilter By CompanyIdFilterTransformAggregate RecommendResponseAggregateRoutingHas Results?1IfTransformEmpty Compare Response1Edit FieldsAI & modelsEmbeddings OpenAI1Embeddings Open AiSubworkflowListCompaniesTool WorkflowWeb / APIList by Facet APIHTTP RequestWeb / APICreate Facet IndexHTTP RequestWeb / APICreate CollectionHTTP RequestTriggerWhen clicking ‘Testworkflow’Manual Trigger

Node categories in this workflow

  • Subworkflow
  • Trigger
  • Routing
  • Web / API
  • Code
  • Transform
  • AI & models
  • Files / media
  • Data store

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
NodeCategoryTypeOperation
InsertSubworkflowTool WorkflowSee node parameters
SearchSubworkflowTool WorkflowSee node parameters
RecommendSubworkflowTool WorkflowSee node parameters
Qdrant MCP ServerTriggerMcp TriggerSee node parameters
When Executed by Another WorkflowTriggerExecute Workflow TriggerSee node parameters
OperationRoutingSwitchSee node parameters
CompareSubworkflowTool WorkflowSee node parameters
Recommend APIWeb / APIHTTP RequestPOST
Get EmbeddingsWeb / APIHTTP RequestPOST
Preferences to ItemsCodeCodeSee node parameters
Aggregate EmbeddingsTransformAggregateSee node parameters
Get Embeddings1Web / APIHTTP RequestPOST
Aggregate Embeddings1TransformAggregateSee node parameters
Group Search APIWeb / APIHTTP RequestPOST
Has Results?RoutingIfSee node parameters
Simplify Group ResultsTransformEdit FieldsSee node parameters
Empty Compare ResponseTransformEdit FieldsSee node parameters
Aggregate Compare ResponseTransformAggregateSee node parameters
Embeddings OpenAIAI & modelsEmbeddings Open AiSee node parameters
Default Data LoaderFiles / mediaDocument Default Data LoaderSee node parameters
Recursive Character Text SplitterTransformText Splitter Recursive Character Text SplitterSee node parameters
Simplify Recommend ResponseTransformEdit FieldsSee node parameters
Get Insert ResponseTransformEdit FieldsSee node parameters
Get Search ResponseTransformAggregateSee node parameters
Insert ReviewsData storeVector Store QdrantSee node parameters
Search ReviewsData storeVector Store QdrantSee node parameters
Split Out CompaniesTransformSplit OutSee node parameters
Filter By CompanyIdRoutingFilterSee node parameters
Aggregate Recommend ResponseTransformAggregateSee node parameters
Has Results?1RoutingIfSee node parameters
Empty Compare Response1TransformEdit FieldsSee node parameters
Embeddings OpenAI1AI & modelsEmbeddings Open AiSee node parameters
ListCompaniesSubworkflowTool WorkflowSee node parameters
List by Facet APIWeb / APIHTTP RequestPOST
Create Facet IndexWeb / APIHTTP RequestPUT
Create CollectionWeb / APIHTTP RequestPUT
When clicking ‘Test workflow’TriggerManual TriggerSee node parameters

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

  • openAiApi
  • qdrantApi

Workflow notes

1. Set up an MCP Server Trigger

1. Set up an MCP Server Trigger

Read more about the MCP Server Trigger

2. Expand Functionality Beyond Vendor Implementation

2. Expand Functionality Beyond Vendor Implementation

Read more about the Qdrant Node

Officially supported MCP servers are cool but may not always have the features you want. N8N MCP servers give you the freedom to expand and customise to fit your business or product needs and requirements.

For our Qdrant MCP server, we've added 2 additional capabilities from the Qdrant API; The Group Search and Recommendation API. With these, we can explore many more use-cases for our users.

🚨Configure Your Qdrant Connection

🚨Configure Your Qdrant Connection

  • Be sure to enter your endpoint address
Try It Out!

Try It Out!

This n8n demonstrates how to build your own Qdrant MCP server to extend its functionality beyond that of the official implementation.

This n8n implementation exposes other cool API features from Qdrant such as facet search, grouped search and recommendations APIs. With this, we can build an easily customisable and maintainable Qdrant MCP server for business intelligence.

This MCP example is based off an official MCP reference implementation which can be found here -https://github.com/qdrant/mcp-server-qdrant/

How it works

  • A MCP server trigger is used and connected to 5 custom workflow tools. We're using custom workflow tools as there is quite a few nodes required for each task.
  • We use a mix of n8n supported Qdrant nodes for simple operations such as insert documents and similarity search, and HTTP node to hit the Qdrant API directly for Facet search, group search and recommendations.
  • We use "Edit Field" and "Aggregate" nodes to return suitable responses to the MCP client.

How to use

  • This Qdrant MCP server allows any compatible MCP client to manage a Qdrant Collection by supporting select and create operations. You will need to have a collection available before you can use this server. Use the Prerequisite manual steps to get started!
  • 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
  • Try the following queries in your MCP client:
    • "Can you help me list the available companies in the collection?"
    • "What do customers say about product deliveries from company X?"
    • "What do customers of company X and company Y say about product ease of use?"

Requirements

  • Qdrant for vector store. This can be an a cloud-hosted instance or one you can self-host internally.
  • MCP Client or Agent for usage such as Claude Desktop - https://claude.ai/download

Customising this workflow

  • Depending on what queries you'll receive, adjust the tool inputs to make it easier for the agent to set the right parameters.
  • Not interested in Reviews? The techniques shared in this template can be used for other types of collections.
  • Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!
Prerequisite: Setup Qdrant Collection

Prerequisite: Setup Qdrant Collection

If you don't have an existing Qdrant Collection, you can use this manual flow to get started.

  1. Creates a collection called "trustpilot_reviews"
  2. Creates an index to allow for facet search ie. list of values of a the "company_id" metadata key.
Always Authenticate Your Server!

Always Authenticate Your Server!

Before going to production, it's always advised to enable authentication on your MCP server trigger.

Prerequisite: Setup Qdrant Collection

Prerequisite: Setup Qdrant Collection

Purpose and structure

This folder contains the Prerequisite: Setup Qdrant Collection workflow. Its executable nodes use aggregate, code, documentDefaultDataLoader, embeddingsOpenAi, executeWorkflowTrigger, filter, httpRequest, if, manualTrigger, mcpTrigger, set, splitOut, switch, textSplitterRecursiveCharacterTextSplitter, toolWorkflow, vectorStoreQdrant. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

Qdrant MCP Server, When Executed by Another Workflow, When clicking ‘Test workflow’

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Splitout/0877_Splitout_Code_Create_Webhook.json MIT; preserve source notices.

More in AI & research

"Hey Siri, Ask Agent" workflow#️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram(G) - Email Classification