How to Use the Elasticsearch Vector MCP in VS Code Copilot

Q: How do we share the Elasticsearch Vector MCP Server configuration across our team in VS Code Copilot?

Create a .vscode/mcp.json file at the root of your shared Git repository. Once committed, every developer on your team using VS Code Copilot gains immediate access to the six vector search tools.

Q: How do I check the configuration of an existing index?

Run the getindex tool from Copilot Chat. It retrieves the index mapping and parameters, showing you the exact distance metric and dimension settings.

Share Elasticsearch Vector search tools across your engineering team directly within VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Elasticsearch Vector to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run cluster-wide vector searches inside VS Code

The `search` tool queries your remote Elasticsearch cluster using dense vectors directly from Copilot Chat. Your engineering team can test vector search queries and analyze top-k recall values without leaving the editor. This direct access speeds up debugging of search relevance issues. Copilot parses the raw JSON search response to explain score distributions and document matches.

Team-wide index management via VS Code Copilot MCP Server

The `create_index` tool allows developers to establish identical index mappings across local, staging, and production environments. You define the vector dimensions in your workspace, and Copilot executes the setup. Listing active environments is simple with the `list_indexes` tool. Copilot displays the active clusters, ensuring your team is pointing to the correct index before running tests.

Index and delete documents from your workspace

The `index_document` tool adds new vector payloads to your Elasticsearch index. This allows you to test how your system handles new embeddings without running external python scripts. Keeping your index clean is easy with the `delete_document` tool. Your agent removes target documents by ID to ensure your search tests run on fresh, unpolluted data.

Setup guide

Set up Elasticsearch Vector MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Elasticsearch Vector MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Elasticsearch Vector tools listed. Try asking: "List my recent Elasticsearch Vector transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "elasticsearch-vector-mcp": {
      "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 VS Code Copilot

Create a `.vscode/mcp.json` file at the root of your shared Git repository. Once committed, every developer on your team using VS Code Copilot gains immediate access to the six vector search tools.

Yes, you can ask Copilot to generate mock embeddings and use the `index_document` tool to insert them. This lets you populate your test indexes directly from the chat interface.

No, you only need VS Code 1.96 or newer and the Copilot extension. The editor natively reads your MCP configuration file and connects to the server.

Run the `get_index` tool from Copilot Chat. It retrieves the index mapping and parameters, showing you the exact distance metric and dimension settings.

Your dense vectors and document payloads are transmitted over secure, encrypted channels directly to your Elasticsearch cluster. Vinkius hosts the MCP server in a zero-trust sandbox, meaning your raw vector data and cluster credentials are never logged or stored.

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