How to Use the Vald MCP in Claude Code

Q: How do I use Vald with Claude Code in a deployment pipeline?

You invoke searchvectors from your shell script. The output is piped directly to subsequent commands, making it ideal for automated, headless workflows in Docker or SSH sessions.

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

Use getvectordetails. This pulls the raw data associated with a specific ID. It’s great for verifying that your script wrote or read the correct information from Vald.

Q: Can Claude Code handle vector deletions in Vald?

Yes, you use deletevector. You must be careful because this action is permanent and irreversible. Always test cleanup scripts thoroughly before running them live.

Q: What information does the MCP Server provide about Vald's operational status?

The getengineinfo tool provides comprehensive details on the Vald engine’s current health and capacity. This helps your CI/CD job determine if it can proceed with vector operations.

Automate complex, headless vector database interactions with Claude Code.

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 Code

Create your Vinkius account to connect Vald to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Perform Vector Similarity Search

The `search_vectors` tool executes a nearest neighbor search against Vald. You supply the query vector as a JSON array of floats, and your script gets back the most similar results. This lets you pipe complex data queries into CI/CD pipelines. Your agent can fetch related records from Vald without needing any graphical interface.

Manage Vector Data Remotely

Need to manage vectors in a script? Use `insert_vector` to add new data, or use `update_vector` for modifications. These actions require the ID and the vector array as input. This allows your backend processes—like cron jobs or GitHub Actions—to treat Vald like any other service endpoint.

Check Vald Engine Status Headlessly

Before running a critical job, you need to know if the database is healthy. The `get_engine_info` tool retrieves operational information and health metrics for the entire Vald engine. Running this check allows your script to fail gracefully if the MCP Server connection drops or performance degrades.

Setup guide

Set up Vald MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see vald-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Vald transactions." It will automatically discover and invoke the available Vald tools.

Terminal

claude mcp add --transport http vald-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "vald-mcp": {
      "type": "url",
      "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 Code

You invoke `search_vectors` from your shell script. The output is piped directly to subsequent commands, making it ideal for automated, headless workflows in Docker or SSH sessions.

Vald handles dense vectors and metadata identifiers. Your scripts interact with this MCP Server by passing JSON arrays of floats to the tool calls.

Use `get_vector_details`. This pulls the raw data associated with a specific ID. It’s great for verifying that your script wrote or read the correct information from Vald.

Yes, you use `delete_vector`. You must be careful because this action is permanent and irreversible. Always test cleanup scripts thoroughly before running them live.

The `get_engine_info` tool provides comprehensive details on the Vald engine’s current health and capacity. This helps your CI/CD job determine if it can proceed with vector operations.

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