How to Use the Vald MCP in Cursor

Q: How do I make sure my Vald searches work with Cursor?

You configure the server in your project's .cursor/mcp.json file, enabling Agent mode. This allows the AI to actively call tools like searchvectors and inject the results directly into the code you're writing.

Q: Can I update a vector definition using Cursor?

Yes. You use the updatevector tool, providing both an existing ID and the new vector array. This is key for keeping your codebase aligned with the latest business rules stored in Vald.

Q: What happens when I run a search query with Vald in Cursor?

The MCP Server executes searchvectors and returns the nearest neighbor results. The unique power here is that Cursor injects this live data directly into your editor, letting you write code that uses real values.

Q: Do I need to worry about configuration when using Vald with Cursor?

You set it up in the .cursor/mcp.json file at the project root or globally. This ensures all team members are working against the same, consistent tools and context.

Write working, context-aware code in Cursor, powered by Vald's vector search capabilities.

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 Cursor

Create your Vinkius account to connect Vald to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject Live Context into Code

When you run a nearest neighbor search using `search_vectors`, the AI client pulls real results from your Vald index. This means the code generated isn't based on mock data; it uses live, retrieved context. This makes debugging and writing API handlers way easier because the code reflects actual database knowledge pulled straight into your editor.

Maintain Code Context Data

Use `insert_vector` when you need to programmatically add a new piece of domain knowledge that should inform your code. You simply provide a unique ID and the vector array, making sure the AI has the latest context. If old patterns are breaking or deprecated, use `delete_vector` to clean up stale data from the Vald index, keeping your generated code accurate.

Check Data State for Team Sync

Before committing a feature, you can check system health using `get_engine_info`. This confirms that the Vald MCP Server is operational and ready for coding tasks. Furthermore, if your code relies on specific data points, calling `get_vector_details` helps confirm what the raw vector structure looks like before writing any API calls.

Setup guide

Set up Vald MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Vald MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Vald transactions." If the MCP tools are loaded correctly, Cursor will call the Vald tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.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 Cursor

You configure the server in your project's `.cursor/mcp.json` file, enabling Agent mode. This allows the AI to actively call tools like `search_vectors` and inject the results directly into the code you're writing.

Yes. You use the `update_vector` tool, providing both an existing ID and the new vector array. This is key for keeping your codebase aligned with the latest business rules stored in Vald.

The MCP Server executes `search_vectors` and returns the nearest neighbor results. The unique power here is that Cursor injects this live data directly into your editor, letting you write code that uses real values.

You set it up in the `.cursor/mcp.json` file at the project root or globally. This ensures all team members are working against the same, consistent tools and context.

This Vald MCP Server handles dense vectors. Anytime your agent reads or writes code that touches Vald, it's dealing with vector representations and associated metadata.

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