How to Use the Azure Cognitive Search MCP in OpenAI Agents SDK

Q: How can my OpenAI Agent search documents in Azure Cognitive Search?

Your agent uses the searchdocuments tool for keyword search or vectorsearch for semantic queries. After you connect this MCP Server, these tools are auto-discovered by your agent, so it can start querying your Azure data immediately.

Q: What's the best way to get a single document from Azure Cognitive Search with an OpenAI Agent?

Use the getdocument tool. Your OpenAI Agent just needs to provide the document's specific key, and the tool will return that single record from Azure Cognitive Search. It's the most direct way to fetch a known item.

Q: Can I use an OpenAI Agent to check the status of my Azure Cognitive Search indexes?

Yes. The agent can use the listindexes and listindexers tools. This allows your OpenAI Agent to get a full picture of your Azure Cognitive Search configuration and the health of your data ingestion pipelines.

Q: What if my agent needs to understand the enrichment pipeline for Azure Cognitive Search?

That's what the listskillsets tool is for. It tells your agent about the Cognitive Services skillsets you have configured, so it knows what kind of AI enrichment is happening to your data.

Equip your OpenAI Agent with production-ready Azure Cognitive Search tools for secure enterprise data access.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Cognitive Search MCP to OpenAI Agents SDK

Create your Vinkius account to connect Azure Cognitive Search to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Azure Cognitive Search with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Enterprise-Grade Search Queries

Give your agent the ability to query your company's knowledge. The `search_documents` tool executes full-text search, while `vector_search` finds information based on meaning, not just keywords. Your agent can finally answer questions using your actual enterprise data in Azure. Because you're using the OpenAI Agents SDK, you can set guardrails that check the agent's planned query before it runs. This prevents it from pulling too much data or running nonsensical searches. You get full visibility into every action through the OpenAI tracing dashboard.

Inspect and Manage Index Health

Your agent can now check on the search infrastructure itself. It uses `list_indexes` and `get_index` to see what indexes exist and what their schemas look like. With `list_indexers`, it can even check the status of data ingestion jobs. This is perfect for building self-monitoring or diagnostic agents. An agent can spot a stalled indexer, find the relevant logs, and alert your team in Slack. This MCP Server gives the agent the awareness it needs to do more than just query data.

Understand Data Enrichment with OpenAI Agents

Go beyond simple search. The `list_skillsets` tool lets your agent see exactly how your data is being processed inside Azure Cognitive Search. It can identify which documents have OCR, entity extraction, or language detection applied. An advanced agent can use this information to form better queries. For example, if it knows a skillset is extracting organization names, it can specifically search for those entities. This turns a simple search tool into a strategic asset for your agent.

Setup guide

Set up Azure Cognitive Search MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Azure Cognitive Search tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Azure Cognitive Search tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Azure Cognitive Search tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Azure Cognitive Search Agent",
            instructions="You have access to Azure Cognitive Search tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Azure Cognitive Search. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Azure Cognitive Search now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Azure Cognitive Search MCP in OpenAI Agents SDK

Your agent uses the `search_documents` tool for keyword search or `vector_search` for semantic queries. After you connect this MCP Server, these tools are auto-discovered by your agent, so it can start querying your Azure data immediately.

Use the `get_document` tool. Your OpenAI Agent just needs to provide the document's specific key, and the tool will return that single record from Azure Cognitive Search. It's the most direct way to fetch a known item.

Yes. The agent can use the `list_indexes` and `list_indexers` tools. This allows your OpenAI Agent to get a full picture of your Azure Cognitive Search configuration and the health of your data ingestion pipelines.

That's what the `list_skillsets` tool is for. It tells your agent about the Cognitive Services skillsets you have configured, so it knows what kind of AI enrichment is happening to your data.

Vinkius manages the connection in an ephemeral, zero-trust sandbox. The MCP Server only touches the specific document contents and index metadata that your agent explicitly requests. Your Azure credentials are never exposed to the agent.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript