Can my agent perform kNN searches using raw vector arrays?

Yes. Use the 'search' tool. Provide the index name and a JSON array representing your query vector. The agent will perform raw K-Nearest Neighbors computations to find the most semantically similar documents.

How do I create a new vector index with specific dimensions via chat?

Use the 'create_index' tool. You can specify the index name and the number of dimensions (e.g., 1536 for OpenAI embeddings). The agent will provision the strictly typed data structure in your Elasticsearch cluster.

Can I delete a single document from a vector index through the agent?

Absolutely. Use the 'delete_document' tool with the index and document ID. The agent will enforce immediate document vaporization, stripping the record from the physical Lucene partitions.

Elasticsearch Vector MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: Elasticsearch Vector
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Elasticsearch Vector through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Elasticsearch Vector Assistant",
            instructions=(
                "You help users interact with Elasticsearch Vector. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Elasticsearch Vector"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Elasticsearch Vector MCP Server

Connect your Elasticsearch cluster to any AI agent and take full control of your vector search and semantic discovery workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 6 tools from Elasticsearch Vector through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Elasticsearch Vector, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

AI-Powered Vector Search — Perform raw K-Nearest Neighbors (kNN) computations mapping absolute semantic similarity across multi-dimensional embedding arrays
Index Orchestration — Enumerate active storage namespaces and validate physical Elasticsearch clusters tracking explicit dimensional shards securely
Schema Management — Analyze specific index mapping rules and provision strictly typed data structures enforcing numeric dimensions for cluster readiness
Document Indexing — Command synchronous bulk insertions attaching exact dense_vector embedding payloads to persist data into raw Lucene partitions
Data Invalidation — Enforce immediate hard document vaporization finding specific exact UUIDs stripping records from physical indices seamlessly
Metadata Auditing — Analyze dimensional constraints and matching similarity thresholds perfectly to verify your vector search configurations

The Elasticsearch Vector MCP Server exposes 6 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Elasticsearch Vector to OpenAI Agents SDK via MCP

Follow these steps to integrate the Elasticsearch Vector MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from Elasticsearch Vector

Why Use OpenAI Agents SDK with the Elasticsearch Vector MCP Server

OpenAI Agents SDK provides unique advantages when paired with Elasticsearch Vector through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Elasticsearch Vector + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Elasticsearch Vector MCP Server delivers measurable value.

Automated workflows: build agents that query Elasticsearch Vector, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Elasticsearch Vector, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Elasticsearch Vector tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Elasticsearch Vector to resolve tickets, look up records, and update statuses without human intervention

Elasticsearch Vector MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect Elasticsearch Vector to OpenAI Agents SDK via MCP:

create_index

Create dense_vector index

delete_document

Delete a document

get_index

Get index info

index_document

Index a document

list_indexes

List all indexes

search

Dense vector knn search

Example Prompts for Elasticsearch Vector in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Elasticsearch Vector immediately.

"Perform a kNN search in index 'product-embeddings' with vector [0.1, 0.2, ...]"

"Create a new vector index 'image-features' with 512 dimensions"

"List all vector indexes in my cluster"

Troubleshooting Elasticsearch Vector MCP Server with OpenAI Agents SDK

Common issues when connecting Elasticsearch Vector to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Elasticsearch Vector + OpenAI Agents SDK FAQ

Common questions about integrating Elasticsearch Vector MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.