How to Use the Vald MCP in Cline

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

Use getvectordetails. It pulls the raw data for a specific ID from Vald. This is crucial when you're writing tests or fixing an issue where the stored vector might be wrong.

Q: What happens if I run an update on Vald through Cline?

If you use updatevector, the system replaces the entire existing record. Always verify the ID and the new vector array before committing, as this changes production data.

Q: How do I ensure my script can delete vectors in Vald using Cline?

You use deletevector. Remember that deleting a vector from the MCP Server is irreversible. It's best to wrap this call in tests first.

Build full-stack features and test vectors with Cline's autonomous execution.

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 Cline

Create your Vinkius account to connect Vald to Cline 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 Cline

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Vector Search Queries

The `search_vectors` tool performs nearest neighbor searches against Vald. Just give it a query vector as a JSON array of floats, and Cline executes the search, returning the most similar data. This means you can tell Cline to 'Build component X using data found by searching vectors in Vald,' and it'll actually write and test that component for you.

Update or Insert Vectors

Need to manage the underlying data? Use `insert_vector` to add a new vector into the Vald index, requiring a unique ID and JSON array. Or use `update_vector` if you've changed an existing record. Cline handles these operations directly, making it possible for your agent to maintain fresh context without manual steps.

Check Database Operational Status

Before running a huge task that relies on vector data, check the health of Vald. The `get_engine_info` tool retrieves current operational status and metrics. This gives you immediate confirmation that the MCP Server is ready to handle your end-to-end task execution, preventing mysterious build failures.

Setup guide

Set up Vald MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type vald-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest Vald refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "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 Cline

Cline's unique power is that it executes the whole task. You ask it to build a dashboard using live room data, and it handles everything—writing code, importing API data, running tests, and interacting with the MCP Server tools like `search_vectors`.

Use `get_vector_details`. It pulls the raw data for a specific ID from Vald. This is crucial when you're writing tests or fixing an issue where the stored vector might be wrong.

Vald deals with dense vectors and their associated IDs, which are passed as JSON arrays. When using this MCP Server, you're manipulating structured vector data within your code execution.

If you use `update_vector`, the system replaces the entire existing record. Always verify the ID and the new vector array before committing, as this changes production data.

You use `delete_vector`. Remember that deleting a vector from the MCP Server is irreversible. It's best to wrap this call in tests first.

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