Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use OpenSearch with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Run k-NN vector searches on OpenSearch. create indexes, upsert embeddings, query similar documents, and manage your vector store from any AI agent.

Included with plan

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

Complete set · 6 capabilities

The complete OpenSearch capability set.

These are the exact actions your AI can choose when you ask it to work with OpenSearch.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through OpenSearch.

  1. 01

    Get index

    Retrieve explicit OpenSearch index mapping and settings

  2. 02

    Index document

    This executes a fast transactional atomic insertion into the embedding space. Upsert a singular vector document directly into an OpenSearch KNN index

  3. 03

    List indexes

    List all explicit indexes residing on the OpenSearch cluster

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through OpenSearch.

  1. 04

    Search

    Provide the exact index name and a JSON-stringified dense float vector array to find conceptually similar embeddings natively. Execute a K-Nearest Neighbors (k-NN) vector search against OpenSearch

  2. 05

    Delete document

    Delete an explicit vector document bounding from OpenSearch

  3. 06

    Create index

    Knn: true` and mapping a rigid dynamic dense vector field optimized for cosine similarity. Create a new native OpenSearch KNN index ready for vector embeddings

Observed, not estimated

847ms average. Fast in production.

OpenSearch is checked daily against the live service.

Daily averagePeak 962ms
Aug 20Today
Fastest day
673ms
Slowest day
962ms
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 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

FAQ

Questions OpenSearch owners ask.

  • 01

    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.

  • 02

    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.

  • 03

    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