How to Use the Vald MCP in Claude

Q: Can I test a new vector insertion using Claude Desktop?

Yep. You can trigger the insertvector tool call via your AI client. Just provide a unique ID and the necessary JSON array for the vector, and Vald handles putting it into the index.

Q: What happens if I run a search query with Vald in Claude Desktop?

The MCP Server executes searchvectors using your provided query vector. It returns the nearest neighbor results from the Vald index, which then feeds live context directly into your chat response.

Q: Is changing data handled by an update tool available in Claude Desktop?

Absolutely. The updatevector function lets you change existing entries using their ID and the new vector array, keeping your knowledge base fresh through the Vald MCP Server.

Get live, structured vector data from your knowledge base right inside Claude Desktop.

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 Claude Desktop

Create your Vinkius account to connect Vald to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Live Nearest Neighbor Searches

You can run a nearest neighbor search using `search_vectors`. Just hand it a query vector as a JSON array of floats, and the MCP Server finds the most similar data points in your Vald index. This means Claude Desktop pulls actual context relevant to your prompt, not generic filler. It's perfect for querying internal documents or finding related API patterns quickly. You don't have to leave the chat to pull real-time knowledge from complex databases.

Manage Your Knowledge Base Entries

Need to keep your source data current? Use `update_vector` with an existing ID and a new vector array. This tool lets you surgically replace stale information in the Vald index without affecting anything else. If the underlying business logic changes, you just update the corresponding vector here. You'll also use `insert_vector` when you need to add brand-new data entries to the knowledge base.

Verify System Health and Data

The MCP Server provides two ways to verify your setup: checking engine health or getting specific details. Call `get_engine_info` to see if Vald is running properly and what its operational status is. You can also get raw data for debugging by calling `get_vector_details`, which retrieves the complete vector data just using a unique ID.

Setup guide

Set up Vald MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Vald MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Vald MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under vald-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 Claude Desktop

You connect to the remote MCP Server URL in the Integrations settings. Once connected, your AI client uses the available tools—like `search_vectors`—to query Vald directly for real-time context within the chat.

Yep. You can trigger the `insert_vector` tool call via your AI client. Just provide a unique ID and the necessary JSON array for the vector, and Vald handles putting it into the index.

The MCP Server executes `search_vectors` using your provided query vector. It returns the nearest neighbor results from the Vald index, which then feeds live context directly into your chat response.

Absolutely. The `update_vector` function lets you change existing entries using their ID and the new vector array, keeping your knowledge base fresh through the Vald MCP Server.

This Vald MCP Server manages dense vectors. When you query or manipulate data, you are 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