How to Use the Elasticsearch Vector MCP in Claude Code

Q: Can I perform a kNN search using Elasticsearch Vector and Claude Code?

Yes. The search tool is available for your terminal commands. It returns the results as JSON that you can pipe into other tools.

Q: Does Elasticsearch Vector support index management in Claude Code?

It does. You can use createindex, getindex, and listindexes to manage your cluster directly from the command line.

Use Claude Code to automate Elasticsearch Vector tasks in your CLI, perfect for CI/CD pipelines and headless data management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elasticsearch Vector MCP to Claude Code

Create your Vinkius account to connect Elasticsearch Vector to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Elasticsearch Vector with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless index management with Claude Code

Run `create_index` and `list_indexes` from your terminal to manage your cluster state. It allows for scripted index deployments during your build process. Claude Code executes these commands without a GUI. It is built for engineers who need to manage their search infrastructure via shell scripts.

Automated vector indexing for Claude Code

Pipe your embedding data into `index_document` to update your search backend automatically. It is designed to handle high-frequency updates from your ingestion pipelines. Use `delete_document` to automate index maintenance. It ensures your search results remain accurate without manual intervention.

Run kNN queries via Claude Code

Integrate vector search into your CLI workflows using the `search` tool. It returns search results directly to your terminal for further processing or logging. This enables you to test retrieval accuracy during local development or in remote CI environments. You get immediate feedback on your search relevance.

Setup guide

Set up Elasticsearch Vector MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see elasticsearch-vector-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Elasticsearch Vector transactions." It will automatically discover and invoke the available Elasticsearch Vector tools.

Terminal

claude mcp add --transport http elasticsearch-vector-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Elasticsearch Vector MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "elasticsearch-vector-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Elasticsearch Vector. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Elasticsearch Vector now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Elasticsearch Vector MCP in Claude Code

Yes. The `search` tool is available for your terminal commands. It returns the results as JSON that you can pipe into other tools.

It connects as an MCP server via HTTP or stdio. Claude Code automatically registers the tools, allowing you to trigger them with simple commands.

It does. You can use `create_index`, `get_index`, and `list_indexes` to manage your cluster directly from the command line.

Vinkius manages all authentication. Every request is tokenized and transported over a secure, private connection.

This server only processes the document vectors and index metadata you provide. It operates in an ephemeral sandbox to ensure no persistent data leaks occur.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript