Can my AI agent do a semantic search across my vector database?

Yes! Provided you supply the embedded query vector, your agent can issue a `vector search` command to the Vald Engine. It will rapidly scan millions of indexes natively using its ANN algorithms and return the top-K closest neighbors associated with your data.

How do I ensure my Vald cluster is healthy right from my CLI?

Skip complex diagnostics loops. Instruct your agent to `get Vald internal engine info`. It will interface directly via gRPC/REST and pull down cluster metrics including operational status, agent versions, and basic diagnostic health. This is vital for MLOps managing production RAG pipelines needing constant reassurance.

Can I permanently purge a corrupted vector embedding?

When a document becomes stale in your knowledge base, you must remove its embedding. Ask the AI agent: `permanently delete vector ID 'doc-xyz'`. Using the `removeVector` capability, it targets your cluster and ensures the outdated semantic representation is fully expunged without risking other node data.

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

Name: Vald
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 Vald through 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="Vald Assistant",
            instructions=(
                "You help users interact with Vald. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Vald"
        )
        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 Vald MCP Server

Connect your Vald cluster to any AI agent and bring distributed, high-speed approximate nearest neighbor (ANN) vector search directly to your conversational workflow.

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

What you can do

Vector Search — Perform rapid semantic searches across millions of embedded data points just by querying the agent.
Data Ingestion — Insert new high-dimensional vectors directly into the Vald index for instant future retrievability in your RAG pipelines.
Index Management — Update the vector representations of existing records or permanently remove specific items from the engine cluster.
Cluster Health — Automatically retrieve operational system information, agent health statuses, and node details regarding your active Vald deployment.

The Vald 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 Vald to OpenAI Agents SDK via MCP

Follow these steps to integrate the Vald 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 Vald

Why Use OpenAI Agents SDK with the Vald MCP Server

OpenAI Agents SDK provides unique advantages when paired with Vald 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

Vald + OpenAI Agents SDK Use Cases

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

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

Multi-agent orchestration: create specialist agents. one queries Vald, another analyzes results, a third generates reports

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

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

Vald MCP Tools for OpenAI Agents SDK (6)

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

delete_vector

This action is irreversible. Permanently removes a vector from the Vald index

get_engine_info

Retrieves operational information and health of the Vald engine

get_vector_details

Retrieves the raw vector data for a specific ID

insert_vector

Provide a unique ID and the vector as a JSON array. Inserts a new vector into the Vald index

search_vectors

Provide a query vector as a JSON array of floats. Performs a nearest neighbor vector similarity search

update_vector

Provide the existing ID and new vector array. Updates an existing vector in the Vald index

Example Prompts for Vald in OpenAI Agents SDK

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

"Is the Vald cluster operational right now?"

"Can you check the vector details stored for UUID 'user-profile-89'?"

"Update the existing item 'context-fragment-12' with this new 1536-dimensional array: [0.38, -0.19, 0...]."

Troubleshooting Vald MCP Server with OpenAI Agents SDK

Common issues when connecting Vald 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.

Vald + OpenAI Agents SDK FAQ

Common questions about integrating Vald 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.