How to Use the Elastic Enterprise Search MCP in Google ADK

Q: How do I restrict which Elastic Enterprise Search tools the Google ADK agent can use?

Use the toolnames filter when initializing the toolset. You can expose search while blocking indexdocuments to prevent the agent from modifying your indices.

Give your Google ADK agents direct access to the Elastic Enterprise Search MCP Server to index, search, and monitor documents.

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 Google ADK

Create your Vinkius account to connect Elastic Enterprise Search to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search and retrieval

The `search` tool pulls exact matches and semantic results from your Elastic deployment. Gemini's massive context window means you can dump hundreds of search results into the prompt without hitting token limits. If you need to audit what's currently stored, the `list_documents` tool grabs the existing records. Your Google ADK agent reads these payloads and cross-references them with data sitting in BigQuery or Vertex AI.

Automated JSON indexing

The `index_documents` tool writes newly created JSON documents into your Elastic schema. Your agent processes raw inputs, structures them, and pushes them straight to the search engine. You skip the manual data pipeline. The agent handles the formatting. Because this runs through the Google ADK, you can take raw logs from Google Cloud, structure them with Gemini, and index them in Elastic in one continuous loop.

Elastic Enterprise Search MCP Server analytics

The `analytics` tool fetches search metrics, top queries, and user click data. The agent analyzes these patterns to figure out what users actually look for. You can also run `list_engines` and `get_engine` to map out the entire search architecture. The agent uses this metadata to decide which engine needs optimization based on the analytics data it just pulled.

Setup guide

Set up Elastic Enterprise Search MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Elastic Enterprise Search tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Elastic Enterprise Search_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Elastic Enterprise Search tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the google-adk package. Set up a McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass this to your LlmAgent under the tools parameter.

Easily. Gemini's long-context reasoning processes massive arrays returned by list_documents or search. It reads the raw JSON and extracts exactly what you ask for.

Use the tool_names filter when initializing the toolset. You can expose search while blocking index_documents to prevent the agent from modifying your indices.

This MCP Server only handles Elastic operations. However, your agent can call this server to get search data and then use native Google tools to write that data into BigQuery.

The V8 Isolate Sandbox ensures that your raw JSON documents and search query logs never persist. The connection terminates immediately after execution, leaving zero residual data in the Vinkius MCP environment.

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