How to Use the DataStax Astra DB Vector MCP in Mastra AI

Q: How can I build a reliable data-sync workflow with DataStax Astra DB Vector and Mastra AI?

Create a Mastra AI workflow that uses the finddocuments tool to check for existing records and insertdocument to add new ones. Mastra AI's built-in retry logic ensures the operations complete even if there are temporary network issues.

Q: Can my Mastra AI agent delete documents from Astra DB?

Yes, using the deletedocument tool. For safety, you can wrap this action in a Mastra AI step that uses the requireToolApproval setting, preventing accidental data loss.

Q: How do I get started with this server in Mastra AI?

After installing the Mastra MCP package, instantiate the MCPClient with your Vinkius server URL. Then call mcpClient.listTools() and pass them to your agent. Mastra handles the rest.

Build resilient data workflows for Astra DB with Mastra AI. Automate document management and vector searches with built-in retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataStax Astra DB Vector MCP to Mastra AI

Create your Vinkius account to connect DataStax Astra DB Vector 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 DataStax Astra DB Vector with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Astra DB Document Workflows

Create workflows that manage your Astra DB data. Use `insert_document` to add new records, then maybe use `find_one_document` to confirm it was written correctly. Mastra AI's workflow engine makes this easy to set up. The real power comes when things go wrong. If an `insert_document` call fails due to a network blip, Mastra AI can automatically retry it with exponential backoff. You don't have to write that logic yourself; your data operations just work.

Branch Workflows Based on Search Results

Don't just run a search; act on the results. A Mastra AI agent can execute a `vector_search`, and if no good matches are found, it can branch to a different step. For example, it could then try a broader search with `find_documents` or flag the item for human review. This lets you build smart, conditional data processing pipelines. You can even use `count_documents` as a preliminary check before starting a heavy compute task. This MCP Server gives your agents the data they need to make decisions.

Build Data-Aware Agents with Mastra AI

Your Mastra AI agents can now interact directly with your vector database. They can use `list_collections` to get a lay of the land before deciding which collection to query. This is key for building agents that can adapt to changing database schemas. You can also require human approval before an agent uses a destructive tool like `delete_document`. Mastra AI's `requireToolApproval` feature combined with this server gives you a safe way to automate database cleanup tasks.

Setup guide

Set up DataStax Astra DB Vector 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 DataStax Astra DB Vector 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: "datastax-astra-db-vector-mcp-client",
  servers: {
    "datastax-astra-db-vector-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent DataStax Astra DB Vector 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 DataStax Astra DB. 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 DataStax Astra DB Vector 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 DataStax Astra DB Vector MCP in Mastra AI

Create a Mastra AI workflow that uses the `find_documents` tool to check for existing records and `insert_document` to add new ones. Mastra AI's built-in retry logic ensures the operations complete even if there are temporary network issues.

Yes, using the `delete_document` tool. For safety, you can wrap this action in a Mastra AI step that uses the `requireToolApproval` setting, preventing accidental data loss.

The server provides the tools; Mastra AI provides the logic. Your agent can use the output of `vector_search` or `count_documents` to decide which branch of your workflow to execute next.

After installing the Mastra MCP package, instantiate the `MCPClient` with your Vinkius server URL. Then call `mcpClient.listTools()` and pass them to your agent. Mastra handles the rest.

Nothing is stored. When your Mastra AI agent calls a tool from the MCP server, the document and collection data passes through a dedicated, isolated Vinkius sandbox for that single operation and is immediately discarded. Your database credentials are never exposed to the agent.

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