How to Use the Vald MCP in Mastra AI

Q: How do I manage data consistency with Vald and Mastra AI?

You should use updatevector when a prior step modifies the necessary context, ensuring that future workflow retries or branches work off accurate information.

Q: Can I check the status of the Vald MCP Server with Mastra AI?

Yes. You call getengineinfo to get operational health metrics for the database engine. This is good practice before deploying a complex, multi-step workflow.

Build reliable, multi-step workflows with Vald and Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Vald to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ensuring Workflow State with the MCP Server

When building complex processes, you need to manage state. Use `update_vector` when your workflow determines that an existing record needs a new vector array. This guarantees the subsequent steps in the chain use the most current information available.

Data Integrity for Mastra AI Workflows

The `insert_vector` tool lets you add brand new vectors with unique IDs into the Vald index. If a workflow step generates new data, you write it here first to ensure persistence before proceeding to the next conditional branch.

Handling Vector Searches in Mastra AI

To make decisions within your multi-step process, run `search_vectors`. This performs a nearest neighbor similarity search using your query vector. The returned context helps the workflow engine decide if it needs to retry or move on.

Setup guide

Set up Vald MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Vald tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "vald-mcp-client",
  servers: {
    "vald-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Vald Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Vald tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Vald transactions"
);
console.log(result.text);

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 Mastra AI

You should use `update_vector` when a prior step modifies the necessary context, ensuring that future workflow retries or branches work off accurate information.

Yes. You call `get_engine_info` to get operational health metrics for the database engine. This is good practice before deploying a complex, multi-step workflow.

The MCP Server handles dense vectors in JSON array format. When running workflows, you are passing and managing vector data to make decisions about process flow.

It's built for it. The combination of reliable workflow management in Mastra AI with structured, searchable vectors from Vald makes sense for automated operations.

The server manages vector data. This includes the raw vector arrays used for searching and the unique IDs assigned when you insert or update vectors.

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