An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Opensearch Vector to ChatGPT, Claude and Gemini

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 your embedding space and run similarity queries through natural language.

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 OpenSearch.

  1. 01

    Get index

    This capability pulls the specific mapping and settings for an OpenSearch index. Use it to check vector dimensions or engine configurations.

  2. 02

    Index document

    This capability performs an atomic upsert of a single vector document. It's the fastest way to add an embedding to your k-NN index.

  3. 03

    List indexes

    This capability returns a list of all indexes currently in your OpenSearch cluster. It's useful for checking index health and document counts.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through OpenSearch.

  1. 04

    Search

    This capability executes a k-Nearest Neighbors search using a dense float vector. It finds the most conceptually similar embeddings in your index.

  2. 05

    Delete document

    This capability removes a specific vector document from your index using its ID.

  3. 06

    Create index

    This capability provisions a new k-NN index optimized for cosine similarity. It sets up the necessary dense vector fields for your embeddings.

Real work

What teams actually run

01

RAG Pipeline Testing

Quickly verify if your retrieved context is accurate by running similarity searches through your agent.

02

Embedding Management

Add or remove specific document embeddings from your vector store as your data changes.

03

Index Monitoring

Check the status and document counts of your various vector indexes using simple text prompts.

04

Rapid Prototyping

Spin up new k-NN indexes with custom dimensions to test different embedding models.

Automate a task

Put OpenSearch 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

OpenSearch 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 OpenSearch 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.

OpenSearch is checked daily against the live service.

Daily averagePeak 1525ms
Oct 3Today
Fastest day
751ms
Slowest day
1525ms
14-day trend
Slowing+80%

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 OpenSearch, so you can see the experience inside your AI.

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

OpenSearch Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_6R4dQ885yexHhsyH4M5e8fLiT1BjuMlzaUlJMumQ/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 — OpenSearch capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "opensearch-vector-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_6R4dQ885yexHhsyH4M5e8fLiT1BjuMlzaUlJMumQ/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 OpenSearch in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work OpenSearch owners hand off.

This MCP is built for technical users who need to bridge OpenSearch clusters with AI-driven workflows.

  • 01

    ML Engineers

    They use the agent to test similarity queries against production embeddings without writing curl commands.

  • 02

    RAG Developers

    They use the agent to index and retrieve context documents for retrieval-augmented generation pipelines.

  • 03

    Data Teams

    They use the agent to inspect index health and vector configurations through conversation instead of dashboards.

FAQ

Questions OpenSearch owners ask.

  • 01

    What is this MCP used for?

    This MCP allows your AI client to perform k-NN vector searches, manage k-NN indexes, and handle document upserts within an OpenSearch cluster.

  • 02

    Which AI clients can I use with this?

    You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I create indexes with specific dimensions?

    Yes, you can instruct your agent to create new k-NN indexes with configurable dimensions such as 384, 768, or 1536.

  • 04

    Does this work with existing OpenSearch clusters?

    Yes, you simply provide your existing host credentials to connect the MCP to your cluster.

  • 05

    How do I perform similarity searches?

    You can ask your agent to execute a k-NN search by providing the index name and a dense float vector.

  • 06

    What vector dimensions does it support?

    Any dimension supported by OpenSearch k-NN. Common values: 384 (MiniLM), 768 (BERT/all-mpnet), 1536 (OpenAI text-embedding-ada-002), 3072 (text-embedding-3-large). When creating an index, specify the exact dimension and the agent provisions the mapping automatically.

  • 07

    Can I delete an entire index or just individual documents?

    Currently, the agent supports deleting individual documents by ID from an index. Full index deletion is not exposed through this integration to prevent accidental data loss. If you need to drop an index, use the OpenSearch Dashboards or direct API calls.

  • 08

    Does this work with Amazon OpenSearch Service (managed)?

    Yes. Provide the Amazon OpenSearch Service endpoint as the host (e.g., https://search-xxx.us-east-1.es.amazonaws.com) along with the master username and password. The integration uses standard REST APIs that work identically on managed and self-hosted clusters.

Explore

More in Loved By Devs

Suggestions

Connect OpenSearch to Claude, Cursor, ChatGPT & more