How to Use the Weaviate MCP in Mastra AI

Q: How do I use Weaviate with Mastra AI for vector search?

You define a sequence: first call getclassschema to ensure the collection exists, then execute searchnearvector. If the search fails due to permission issues, Mastra AI handles the backoff and retry logic.

Q: What happens when I need the full schema in Mastra AI?

You include getfullschema as a mandatory first step. This ensures that every subsequent tool call—like listing objects or checking details—knows the scope of your Weaviate instance.

Build reliable, complex Weaviate workflows with 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 Weaviate MCP to Mastra AI

Create your Vinkius account to connect Weaviate 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 Weaviate with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Multi-Step Workflows on the MCP Server

Mastra AI manages multi-step processes. You can build a workflow that first calls `get_class_schema` to validate inputs, then uses `search_near_vector` to find relevant data objects. If any step fails—like an invalid schema name—the system automatically retries the operation.

Manage State and Retry Failures with Weaviate MCP Server

The server handles operational checks like `get_cluster_nodes`. Mastra AI can wrap these calls in a conditional branch: if node status is unhealthy, it automatically retries the check later. This guarantees your workflow doesn't fail just because of temporary network hiccups.

Retrieve Object Details for Auditing Workflows

Need to confirm exactly which record was processed? Use `get_object_details` within a Mastra AI workflow. This allows you to audit the state change after an action, ensuring your complex operational steps complete successfully and reliably.

Setup guide

Set up Weaviate 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 Weaviate 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: "weaviate-mcp-client",
  servers: {
    "weaviate-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Weaviate 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 Weaviate. 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 Weaviate 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 Weaviate MCP in Mastra AI

You define a sequence: first call `get_class_schema` to ensure the collection exists, then execute `search_near_vector`. If the search fails due to permission issues, Mastra AI handles the backoff and retry logic.

Yes. The ability of Mastra AI to handle conditional branching means you can build sophisticated processes: check cluster nodes, then search data objects, and only proceed if both checks pass.

You include `get_full_schema` as a mandatory first step. This ensures that every subsequent tool call—like listing objects or checking details—knows the scope of your Weaviate instance.

Mastra AI supports calling any available MCP tool. You can use everything from `list_objects` for pagination checks to the core vector search capabilities.

This server processes the UUIDs and structured content of data objects. Mastra AI's ability to retry operations means it handles reading these object details repeatedly for verification purposes.

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