How to Use the Vertex AI Search MCP in Claude

Q: How do I get an answer using Vertex AI Search in Claude Desktop?

Just send your query and let the agent call getgroundedanswer. The result will be a natural language response that points back to the source documents, so you know where the info came from.

Q: Can Vertex AI Search list my existing data stores in Claude Desktop?

Absolutely. You use listdatastores to see everything set up for your organization. It’s a quick way to check if you've indexed all the necessary internal documentation.

Q: What if I need recommendations using Vertex AI Search in Claude Desktop?

You run getrecommendations. This tool needs two things: the data store ID and a JSON object detailing user events. Your agent builds that payload for you.

Get grounded answers in Claude Desktop. Your AI client connects to your private enterprise knowledge.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vertex AI Search MCP to Claude Desktop

Create your Vinkius account to connect Vertex AI Search to Claude Desktop 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 Vertex AI Search with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Retrieve grounded answers with the MCP Server.

When you call `get_grounded_answer`, your AI client reads a natural language response directly from your data store. It doesn't guess; it cites specific information found in your private documents. This is perfect for enterprise knowledge bases. You send the query, and Claude Desktop delivers an answer backed up by source material.

Find what you need across all data stores.

Need to know what's available? Use `list_data_stores` to get a rundown of every collection in your Vertex AI Search setup. This gives you a map of where your company data lives. From there, you can narrow it down by calling `list_search_engines`, making sure Claude Desktop targets the right search mechanism.

Get personalized recommendations using the MCP Server.

`get_recommendations` pulls relevant suggestions based on user actions. You provide a specific data store ID and JSON of recent user events. Your agent uses this context to give highly tailored results, which is way better than generic search hits.

Setup guide

Set up Vertex AI Search MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Vertex AI Search MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Vertex AI Search MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under vertex-ai-search-mcp.

json

{
  "mcpServers": {
    "vertex-ai-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 Vertex AI 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 Vertex AI 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 Vertex AI Search MCP in Claude Desktop

Just send your query and let the agent call `get_grounded_answer`. The result will be a natural language response that points back to the source documents, so you know where the info came from.

Absolutely. You use `list_data_stores` to see everything set up for your organization. It’s a quick way to check if you've indexed all the necessary internal documentation.

You run `get_recommendations`. This tool needs two things: the data store ID and a JSON object detailing user events. Your agent builds that payload for you.

Yes, because it's an MCP Server running locally or remotely connected via URL, your AI client handles the connectivity to Vertex AI Search. It works whether you're on the native app or using a custom connector.

This server primarily touches indexed document content and associated metadata, specifically the documents within your defined data stores.

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