How to Use the Vald MCP in Windsurf

Q: What is the best way to delete old data in Vald using Windsurf?

Use deletevector. Just remember this is a destructive action. Always confirm you want to remove a vector permanently before letting Cascade run it, because there's no undo.

Q: If I need vector details for debugging with Vald and Windsurf, which tool do I use?

The getvectordetails tool is what you want. It pulls the raw vector data for a specific ID, letting you verify exactly what was stored in your MCP Server index.

Chain complex vector queries and data manipulations using Windsurf.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to Windsurf

Create your Vinkius account to connect Vald 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 Vald with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Vector Similarity Searches

The `search_vectors` tool finds the nearest neighbor vectors in Vald. Give it a query vector as a JSON array of floats, and Cascade immediately returns the most similar data points. This is perfect for finding related documents or context when you're building an agent. Windsurf uses this output to continue its workflow automatically, so you don't have to prompt the next step.

Manage Vector Index Data

Need to change something? Use `update_vector` to modify existing data in Vald. You just supply an ID and a new vector array, and it handles the replacement. Alternatively, if the data is garbage or obsolete, you can use `delete_vector`. Remember, this action is irreversible, so double-check your plan before letting Cascade run that.

Monitor Vald Engine Health

Before running a massive query, check the system status. The `get_engine_info` tool pulls operational data and health metrics for the entire Vald engine. This gives you confidence that your MCP Server connection is solid. It lets you know if there are any resource bottlenecks before your autonomous agent starts chaining complex actions.

Setup guide

Set up Vald 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 Vald 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 Vald payment history." If connected, Cascade will call the Vald tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "vald-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 Vald. 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 Vald 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 Vald MCP in Windsurf

Windsurf's Cascade system reads the context and automatically manages the state between tools. It doesn't stop waiting for you to prompt; it plans a multi-step sequence using the MCP Server tools, executes them all, and shows you the final result.

Yes. Since Windsurf is an IDE agent, it's best for local development, but its ability to chain multi-tool actions makes the MCP Server useful when simulating pipeline steps within your environment.

Vald handles dense vectors and associated metadata. When connecting the MCP Server, you're working with JSON arrays for vector input and output, which Cascade then integrates into your overall codebase.

Use `delete_vector`. Just remember this is a destructive action. Always confirm you want to remove a vector permanently before letting Cascade run it, because there's no undo.

The `get_vector_details` tool is what you want. It pulls the raw vector data for a specific ID, letting you verify exactly what was stored in your MCP Server index.

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