An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Vertex AI Vector Search to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage and query massive vector datasets directly from your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Vertex AI Vector Search.

  1. 01

    List deployed indexes

    This capability pulls a list of all indexes currently deployed to a specific endpoint.

  2. 02

    List index endpoints

    Use this to see every index endpoint active within your Google Cloud project.

  3. 03

    List vector operations

    This capability retrieves the status of long-running operations related to your vector indexes.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Vertex AI Vector Search.

  1. 04

    Get index details

    This capability fetches the specific metadata and configuration settings for a single vector index.

  2. 05

    List vector indexes

    This capability provides a full list of all vector indexes residing in your Google Cloud project.

  3. 06

    Search nearest neighbors

    This capability performs a similarity search by passing an endpoint ID, index ID, and a JSON array vector.

Real work

What teams actually run

01

RAG Grounding

Your agent performs nearest neighbor lookups to pull relevant context for LLM responses.

02

Deployment Monitoring

You track the status of massive index builds while you continue writing code in your editor.

03

Infrastructure Audits

You verify the dimensionality and configuration of production indexes via simple text commands.

04

Vector Proximity Testing

You test how well specific vectors map to existing data by querying endpoints directly.

Automate a task

Put Vertex AI Vector Search to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Vertex AI Vector Search works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Vertex AI Vector Search to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

916ms average. Fast in production.

Vertex AI Vector Search is checked daily against the live service.

Daily averagePeak 1114ms
Oct 3Today
Fastest day
668ms
Slowest day
1114ms
14-day trend
Slowing+18%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Vertex AI Vector Search, so you can see the experience inside your AI.

It does not authenticate your account with Vertex AI Vector Search. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Vertex AI Vector Search Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_7qmxXVVjzgLzy5Qveg1Au3aDsjeacjAMcHp2XBIt/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Vertex AI Vector Search capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "vertex-ai-vector-search-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_7qmxXVVjzgLzy5Qveg1Au3aDsjeacjAMcHp2XBIt/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Vertex AI Vector Search in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Vertex AI Vector Search owners hand off.

This MCP is built for technical users managing large-scale vector databases in Google Cloud.

  • 01

    MLOps Engineers

    They hand off index deployment monitoring and cluster status checks to the agent.

  • 02

    RAG Data Scientists

    They use the agent to test vector proximity and push experimental arrays to production endpoints.

  • 03

    Backend Architects

    They delegate infrastructure verification and shard configuration audits to the agent.

FAQ

Questions Vertex AI Vector Search owners ask.

  • 01

    How do I use this MCP with my existing Google Cloud setup?

    You need to enable the Vertex AI API for your project and provide your Project ID, Location, and an OAuth2 Access Token to the MCP.

  • 02

    Can I use this to search through billions of embeddings?

    Yes, this MCP allows your agent to perform nearest neighbor lookups across massive, billion-scale embedding structures hosted on Vertex AI.

  • 03

    Do I still need to use the Google Cloud Console?

    While you can still use the console, this MCP lets you perform most index management, monitoring, and search tasks directly from your AI client.

  • 04

    What kind of clients can connect to this MCP?

    Any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code, can connect to this capability.

  • 05

    Can I monitor long-running index builds?

    Yes, you can use the capability to query the cloud queue and review the timelines for long-running vector operations.

  • 06

    How do I perform a nearest-neighbor similarity test via chat?

    Just write: Search my endpoint '1xxx' against index 'deployed_abc_1' looking for 3 nearest neighbors to the vector [0.015, -0.042, 0.111]. The queryIndexTool bridges to Vertex and returns the IDs and distances of your geometrical matches instantly.

  • 07

    Can I query a status for indices that take hours to build on GCP?

    Absolutely. Use the prompt: Check my google cloud vector operations. The listOperationsTool reveals all in-flight Cloud operations indicating completion percentages and precise timestamps, allowing you to sidestep the Google Console completely.

  • 08

    Where do I easily find the short-lived VERTEX_ACCESS_TOKEN?

    On your terminal with gcloud installed and logged in, simply type gcloud auth print-access-token. Copy the output stream starting with ya29... into your configurations and the integration is ready for connection.

Explore

More in AI Frontier

Suggestions

Connect Vertex AI Vector Search to Claude, Cursor, ChatGPT & more