How to Use the Vertex AI Search MCP in Windsurf

Q: How do I search my internal data using Vertex AI Search and Windsurf?

You use the searchdocuments tool. You give it a specific data store ID and your query text, and Windsurf returns results from your enterprise documents.

Q: Can Windsurf list all available private document sources with Vertex AI Search?

Yep. The listdatastores tool lists every collection you have set up in the Vertex AI Search backend, giving you a full inventory of where your data lives.

Q: Does Vertex AI Search support document listing inside Windsurf?

Absolutely. The listdatastoredocuments tool lets you see all individual files within a given data store branch ID, giving you granular visibility into the indexed material.

Ground your AI answers with Vertex AI Search, right inside Windsurf's autonomous agent.

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 Windsurf

Create your Vinkius account to connect Vertex AI 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 Vertex AI Search with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Windsurf: Grounded Q&A

The `get_grounded_answer` tool returns a natural language response based on your private data. If you ask an open-ended question, Cascade automatically finds the relevant documents and builds an answer supported by those sources. You don't have to tell it which tools run in sequence. Just set the goal—like 'Explain Q3 revenue trends'—and Windsurf handles the multi-step search process.

MCP Server: Data Store Listing

Need to know what data you have indexed? Use `list_data_stores` to list every single data store in your collection. This shows Cascade all potential sources it can draw from before running a search. It's also good for checking scope when you run `list_search_engines`. Knowing the available engines lets Windsurf select the right mechanism for its plan.

Windsurf: Personalized Recommendations

The `get_recommendations` tool gives you personalized suggestions based on user events. You simply pass a data store ID and the user event JSON object to make it work. This is perfect for building features that anticipate user needs, like suggesting next articles or products right when Windsurf's agent runs.

Setup guide

Set up Vertex AI 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 Vertex AI 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 Vertex AI Search payment history." If connected, Cascade will call the Vertex AI Search tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You use the `search_documents` tool. You give it a specific data store ID and your query text, and Windsurf returns results from your enterprise documents.

Yep. The `list_data_stores` tool lists every collection you have set up in the Vertex AI Search backend, giving you a full inventory of where your data lives.

This server works directly with indexed documents. It reads metadata and content from the specific data stores configured in your environment.

Absolutely. The `list_datastore_documents` tool lets you see all individual files within a given data store branch ID, giving you granular visibility into the indexed material.

The MCP Server provides the actual connection point for the search logic. When Cascade executes a goal, it calls the necessary tools—like `get_grounded_answer`—on this server to get the grounded output.

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