Elasticsearch Vector Connector for AI agents.
6 live capabilities
Manage your vector search and semantic discovery workflows with natural language commands.
Waiting for input…
Why people use Elasticsearch Vector
Elasticsearch Vector for Semantic Search Management
This Connector changes that by letting you stay in your chat or IDE. You just tell your agent to search for something similar or list your current indexes. You get immediate results and can manage your entire Elasticsearch vector setup through a simple conversation.
What Vinkius changes
That you turn your Elasticsearch cluster into a conversational vector database.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Testing new embeddings
An AI Engineer wants to see how a new model performs.
- Real-world use case 02
Rapid prototyping
A dev needs a search feature.
- Real-world use case 03
Database Auditing
An Ops lead needs to check the cluster.
Complete set · 6capabilities
The complete Elasticsearch Vector capability set.
These are the exact actions your AI can choose when you ask it to work with Elasticsearch Vector.
01—03
3 capabilities in this set.
Part of 6 available through Elasticsearch Vector.
- 01 Capability
Search
Run a dense vector kNN search to find semantically similar documents. This helps you find relevant results based on vector similarity.
- 02 Capability
List indexes
See every active index in your Elasticsearch cluster. This provides a quick overview of your current storage namespaces.
- 03 Capability
Get index
Look up the specific mapping and dimension details for a single index. Use this to verify your configuration before indexing.
04—06
3 capabilities in this set.
Part of 6 available through Elasticsearch Vector.
- 04 Capability
Index document
Add a new document with its dense_vector embedding to your storage. This handles the insertion into your Lucene partitions.
- 05 Capability
Delete document
Remove a specific record from your physical index using its UUID. This is the fastest way to invalidate specific data.
- 06 Capability
Create index
Set up a new dense_vector index with the correct number of dimensions. This allows you to provision new search structures quickly.
Set up in minutes
One URL. Then ask Elasticsearch Vector to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Elasticsearch Vector from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Elasticsearch Vector, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Elasticsearch Vector for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Elasticsearch Vector URL.
- Step 03
Save and start
Save the connection and enable Elasticsearch Vector in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"elasticsearch-vector": {
"url": "https://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Elasticsearch Vector
Open Agent mode in chat and ask: "Using Elasticsearch Vector, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"elasticsearch-vector": {
"url": "https://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Elasticsearch Vector
Ask Copilot: "Using Elasticsearch Vector, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"elasticsearch-vector": {
"url": "https://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Elasticsearch Vector
Open Cascade and ask: "Using Elasticsearch Vector, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"elasticsearch-vector": {
"url": "https://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Elasticsearch Vector
Ask Cline: "Using Elasticsearch Vector, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add elasticsearch-vector --transport http "https://edge.vinkius.com/vk_preview_kUWPWShL0BRuDE0k7qrS1ZYbK8Cj21vwQZnEsEiQ/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Elasticsearch Vector
Ask Claude: "Using Elasticsearch Vector, show me...". 6 tools are ready
Where the request belongs
Work Elasticsearch Vector can move forward.
This is for the engineers and data scientists who are tired of writing boilerplate query code just to see if their embeddings actually work. It's for the people who need to manage production vector data without leaving their chat interface.
AI Engineer
Testing new embedding models and verifying kNN results without writing complex DSL.
Software Developer
Indexing documents and checking search similarity directly from the IDE or chat.
Data Scientist
Monitoring index mappings and dimensional constraints using natural language.
Ops Engineer
Verifying cluster health and managing vector namespaces in real-time.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsOpenSearch Vector
Run k-NN vector searches on OpenSearch. create indexes, upsert embeddings, query similar documents, and manage your vector store from any AI agent.
Vertex AI Vector Search
Bring Google's massive vector matching power to your AI agent. Search billions of semantic embeddings and administer Vertex Index endpoints directly in chat.
Redis Vector
Equip your AI to autonomously manage embeddings, run KNN similarity searches, and administrate vector indexes natively inside your Redis stack.
Milvus (Open-Source Vector Database)
Manage vector storage via Milvus. perform ANN searches, query scalar entities, and audit collections.
Typesense Vector Search
Automate vector similarity searches via Typesense. index documents, manage collections, and execute semantic queries directly from your AI agent.
Qdrant
Empower your AI to interact directly with your Qdrant vector database. query clusters, perform similarity searches, and manage collections effortlessly.
Bring your own AI
Change the model, client or framework. Keep Elasticsearch Vector connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Elasticsearch Vector.
The practical details behind the request, access and result.
Can the Elasticsearch Vector MCP help me manage my embeddings?
Yes, it lets your agent handle the indexing and searching of your dense vector data directly, making it easy to manage your embeddings without manual scripts.
How do I connect my Elasticsearch cluster to my AI agent?
You just need your Host URL and an API Key from your Kibana security settings to link the Connector to your AI client.
Does this Connector support kNN searches?
It specifically handles dense vector kNN computations to find the most similar items in your data based on semantic similarity.
Can I use this to delete specific records?
You can use the delete capability to remove documents from your physical indices using their unique UUIDs, which is great for data cleanup.
Is this good for checking my index mappings?
Yes, it allows your agent to pull and display the specific rules and dimensions for any index in your cluster to ensure your configuration is correct.
Can my agent create new vector indexes for me?
It can provision new dense_vector structures with the exact dimensions you specify in plain English, saving you from manual configuration.
Can my agent perform kNN searches using raw vector arrays?
Yes. Use the 'search' capability. Provide the index name and a JSON array representing your query vector. The agent will perform raw K-Nearest Neighbors computations to find the most semantically similar documents.
How do I create a new vector index with specific dimensions via chat?
Use the 'create_index' capability. You can specify the index name and the number of dimensions (e.g., 1536 for OpenAI embeddings). The agent will provision the strictly typed data structure in your Elasticsearch cluster.
Can I delete a single document from a vector index through the agent?
Absolutely. Use the 'delete_document' capability with the index and document ID. The agent will enforce immediate document vaporization, stripping the record from the physical Lucene partitions.
One connection away
Give your agent a direct line to Elasticsearch Vector.
Connect Elasticsearch Vector once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available