How to Use the Marqo AI (Vector Search & Embeddings) MCP in Windsurf

Let Windsurf's Cascade agent build and manage your entire Marqo AI semantic search backend, from indexing to querying.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqo AI (Vector Search & Embeddings) MCP to Windsurf

Create your Vinkius account to connect Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Vector Indices Autonomously

Point Windsurf at your data and tell it to create a search index. Cascade plans the whole job, starting with `create_index` to set up a new Marqo vector index with the right settings. Then, it gets to work. Cascade reads your files or database records and automatically batches them for the `add_documents` tool, populating your new index without you writing a single line of code.

Find Anything with Natural Language

This MCP server connects Windsurf directly to Marqo's `tensor_search`. You don't prompt it to run a query; you just ask a question about your documents, and Cascade figures out the rest. It translates your goal into a precise `tensor_search` operation. The results come back right in your IDE, ready for the next step of whatever task you're working on.

Your MCP Server for Index Operations

Managing vector indices is part of the job. Ask Windsurf to 'show me all the Marqo indexes,' and it runs `list_indexes` to give you a complete inventory right in the agent's response. Need to check on a specific index's health? Tell it to get the stats for 'product-catalog', and it uses `get_index_stats` to report the document count and configuration. It can even handle cleanup by using `delete_documents` to remove stale data.

Setup guide

Set up Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) payment history." If connected, Cascade will call the Marqo AI (Vector Search & Embeddings) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "marqo-ai-vector-search-embeddings-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 Marqo AI. 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) MCP in Windsurf

Windsurf's Cascade agent chains tools together autonomously. You state a goal like 'index my blog for search,' and it automatically runs `create_index` then `add_documents` without you prompting each step.

Try this: 'Create a Marqo index named 'test-index', add a document with the content 'hello world' to it, and then search for 'greetings planet'. Windsurf will chain `create_index`, `add_documents`, and `tensor_search` to do it.

Yes. You can give it a multi-step goal like, 'delete the old documents from the 'products' index, then add these new ones.' Cascade will use `delete_documents` and `add_documents` in sequence to complete the job.

Windsurf shows you its plan before it executes. You'll see each tool call, like `get_index_stats` or `tensor_search`, listed out before the agent runs the sequence against this MCP server.

The server only processes the document contents you send via `add_documents` and the query text for `tensor_search`. Vinkius isolates each request in an ephemeral sandbox, and your auth token is the only thing connecting you to the operation. No data is stored past the request's lifetime.

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