How to Use the Azure AI Search MCP in Windsurf

Q: Can Windsurf run vector similarity queries on Azure AI Search?

Yes, Windsurf calls the vectorsearch tool to execute similarity queries. Cascade handles the vector math parameters and processes the returned documents inside your chat.

Stop manually querying Azure. Let Windsurf and Cascade chain search queries and index audits autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure AI Search MCP to Windsurf

Create your Vinkius account to connect Azure AI Search to Windsurf 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 AI Search with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Azure AI Search indexes inside Windsurf

The `list_indexes` tool fetches every active Azure AI Search index in your cloud subscription so Cascade can map out your search architecture. From there, the Windsurf agent uses `get_index` to pull the exact JSON schema configurations without forcing you to open the Azure Portal. Cascade uses this structural Azure data to write better queries. Because Windsurf understands the field types and search analyzer setups directly, it writes code that matches your actual Azure search fields the first time.

Run hybrid search queries with Windsurf Cascade

The `search_documents` tool runs full-text lexical queries, while `vector_search` executes high-dimensional similarity searches. By chaining these two Azure AI Search operations, Cascade compares results and finds the most relevant documents for your current Windsurf workspace. You just ask Cascade to fix an Azure search relevancy bug. The agent runs the queries, analyzes the score disparities, and edits your backend retrieval code inside Windsurf in one continuous loop.

Debug data ingestion using this MCP Server

The `list_indexers` tool exposes the current status of your scheduled Azure indexers, while `list_datasources` reveals the exact source locations feeding those indexes. Cascade checks these endpoints to trace why new database records aren't showing up in your Azure AI Search results. Instead of guessing if an Azure ingestion run failed, you let Windsurf handle the diagnostics. Cascade spots the broken run, identifies the source mismatch, and suggests the fix.

Setup guide

Set up Azure AI Search MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Azure AI Search MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Azure AI Search payment history." If connected, Cascade will call the Azure AI Search tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "azure-ai-search-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 AI 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 AI 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 AI Search MCP in Windsurf

Windsurf uses this MCP Server to query your indexes directly from Cascade. Cascade calls the tools to retrieve schemas or run document searches, integrating the results straight into your active workspace.

Yes, Windsurf calls the `vector_search` tool to execute similarity queries. Cascade handles the vector math parameters and processes the returned documents inside your chat.

No, Vinkius manages the authentication layer securely. You only need to add your single Vinkius MCP Server endpoint token to your Windsurf configuration file to grant Cascade access.

Yes, you can ask the agent to inspect your pipelines. It uses the `list_indexers` tool to fetch the current run state and logs.

Your raw document payloads and schema configurations never persist outside your session. Vinkius runs the connector in an isolated, ephemeral sandbox that destroys all index data the moment your query finishes.

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