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.

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.

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.

OpenSearch Vector MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: OpenSearch Vector
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect OpenSearch Vector through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

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

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to OpenSearch Vector "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in OpenSearch Vector?"
    )
    print(result.data)

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 OpenSearch Vector MCP Server

Turn your OpenSearch cluster into an AI-native vector database. Create k-NN indexes, upsert embeddings, run similarity searches, and inspect index configurations — all through natural conversation with your AI agent.

Pydantic AI validates every OpenSearch Vector tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Vector Search — Execute k-Nearest Neighbors queries against any k-NN index with custom top-K limits and dense float vectors
Index Management — List all cluster indexes with health status and document counts, or inspect a specific index's vector dimension, engine config, and distance metric
Create Index — Provision new k-NN indexes optimized for cosine similarity with configurable vector dimensions (384, 768, 1536, etc.)
Document Operations — Upsert vector documents with metadata, or delete documents from the embedding space by ID

The OpenSearch Vector MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI 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 OpenSearch Vector to Pydantic AI via MCP

Follow these steps to integrate the OpenSearch Vector MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from OpenSearch Vector with type-safe schemas

Why Use Pydantic AI with the OpenSearch Vector MCP Server

Pydantic AI provides unique advantages when paired with OpenSearch Vector through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your OpenSearch Vector integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your OpenSearch Vector connection logic from agent behavior for testable, maintainable code

OpenSearch Vector + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the OpenSearch Vector MCP Server delivers measurable value.

Type-safe data pipelines: query OpenSearch Vector with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple OpenSearch Vector tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query OpenSearch Vector and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock OpenSearch Vector responses and write comprehensive agent tests

OpenSearch Vector MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect OpenSearch Vector to Pydantic AI via MCP:

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

delete_document

Delete an explicit vector document bounding from OpenSearch

get_index

Retrieve explicit OpenSearch index mapping and settings

index_document

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

list_indexes

List all explicit indexes residing on the OpenSearch cluster

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

Example Prompts for OpenSearch Vector in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with OpenSearch Vector immediately.

"List all vector indexes in my OpenSearch cluster."

"Find the 5 most similar documents to this embedding in the knowledge-base index."

"Create a new k-NN index called 'customer-feedback' with 1536 dimensions."

Troubleshooting OpenSearch Vector MCP Server with Pydantic AI

Common issues when connecting OpenSearch Vector to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

OpenSearch Vector + Pydantic AI FAQ

Common questions about integrating OpenSearch Vector MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your OpenSearch Vector MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.