How to Use the Elastic Enterprise Search MCP in Windsurf

Q: How does Windsurf run multiple Elastic Enterprise Search operations in a single run?

Cascade reads your intent and chains tools like listengines and search without asking for step-by-step confirmation. It fetches the engine list, selects the target, and runs the query in one automated sequence.

Q: Where do I configure the Elastic Enterprise Search MCP Server in Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server config under the mcpServers key. You can also use the Settings UI under Cascade MCP Servers to paste your endpoint token.

Q: How do I inspect specific engine details before running queries?

Use the getengine tool to pull metadata about a specific search engine. This lets your agent inspect active languages, document counts, and schema types before writing search queries.

Query, index, and monitor search metrics directly inside Windsurf using Cascade's multi-step autonomous planning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elastic Enterprise Search MCP to Windsurf

Create your Vinkius account to connect Elastic Enterprise Search to Windsurf 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 Elastic Enterprise Search with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Elastic Enterprise Search queries directly inside Windsurf

The `search` tool executes search queries across your Elastic engines without leaving your editor. Cascade takes your prompt, identifies the target engine, and fetches raw document matches instantly. It handles raw JSON structures directly in the active editor pane. You can also list existing documents using `list_documents` to verify what is inside an engine before writing custom query parsers. Cascade chains this check before runs, saving you from manual API testing cycles when debugging query payloads.

Let Cascade index new documents with this MCP Server

The `index_documents` tool pushes JSON payloads into your Elastic engines directly from your workspace. When you generate new mock data or migrate schemas, your agent structures the payload and runs the ingestion step autonomously. It checks the target schema, formats the JSON, and executes the call. Before pushing data, Cascade uses `list_engines` to verify the destination exists. If the engine is missing, it flags the issue immediately rather than letting the indexing call fail silently in the background.

Track search performance metrics within your IDE

The `analytics` tool fetches real-time search performance logs and click metrics from your Elastic cluster. Cascade reads these raw analytics reports to identify failed user queries or low-click terms. It then suggests schema modifications or synonym updates based on actual user behavior. Your agent links these metrics to specific engine configurations retrieved via `get_engine`. This lets you diagnose search relevance issues directly from the Windsurf sidebar without loading the Elastic Cloud console.

Setup guide

Set up Elastic Enterprise Search MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Elastic Enterprise Search 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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Elastic Enterprise Search payment history." If connected, Cascade will call the Elastic Enterprise Search tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "elastic-enterprise-search-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 Elastic Enterprise Search. 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 Elastic Enterprise Search 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 Elastic Enterprise Search MCP in Windsurf

Cascade reads your intent and chains tools like `list_engines` and `search` without asking for step-by-step confirmation. It fetches the engine list, selects the target, and runs the query in one automated sequence.

Yes. Cascade reads your local workspace files, parses the JSON schema, and invokes the `index_documents` tool to push them to your engine. It handles formatting and payload validation before sending the request.

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server config under the `mcpServers` key. You can also use the Settings UI under Cascade MCP Servers to paste your endpoint token.

Use the `get_engine` tool to pull metadata about a specific search engine. This lets your agent inspect active languages, document counts, and schema types before writing search queries.

Vinkius runs the server inside a zero-trust V8 Isolate sandbox, ensuring your indexed JSON payloads never persist on external disks. Your API keys are injected at the gateway level, keeping sensitive search logs and document schemas isolated from unauthorized network hops.

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