How to Use the DataDome MCP in Mastra AI

Q: Can Mastra AI automatically retry DataDome API calls?

Yes. If a tool like getprotectionstats fails due to network issues, Mastra uses built-in exponential backoff to try again. Your workflow will not crash from a simple timeout.

Q: How do I find all applications protected by DataDome?

Run the listprotectedapplications tool. It returns the application names, protection types, and masked API keys for your mobile and web properties.

Build resilient, multi-step bot mitigation workflows in Mastra AI using DataDome telemetry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataDome MCP to Mastra AI

Create your Vinkius account to connect DataDome 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 DataDome with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate endpoint health checks

The `get_endpoint_health` tool fetches latency metrics and error rates for your protected endpoints. Mastra AI uses this data to trigger conditional workflows. If latency spikes or the operational state degrades, the agent can automatically alert an admin. You can pair this with `get_bot_traffic_summary` to see if good bots or scrapers are causing the load. Mastra handles the retries automatically if the MCP Server times out during a massive spike in traffic.

Build conditional threat responses via Mastra AI

Your agent pulls recent security incidents using the `list_recent_threats` tool. It gets the origin IPs and threat types right away. If it spots a credential stuffing attack, Mastra's workflow engine branches the logic to notify the security team. Before taking action, the agent can verify existing defenses with `list_custom_bot_rules`. It checks the match criteria and priority levels. You can set up requireToolApproval in Mastra to keep a human in the loop before modifying any rules based on this MCP Server data.

Isolate specific attack vectors

Calling `search_threats_by_type` through the MCP Server filters recent incidents down to specific keywords like crawler or scraper. Mastra AI executes this search as a step in your automated audit pipeline. If a specific threat type spikes, the agent moves to the next node in the workflow. It then pulls the exact request headers and behavioral patterns using `get_threat_details`. The workflow engine compiles these details into a structured report and ships it to your alerting system.

Setup guide

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

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

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

Install @mastra/mcp. Initialize the MCPClient with your Vinkius endpoint URL. Call listTools() and spread the results into your Mastra agent configuration.

Yes. If a tool like get_protection_stats fails due to network issues, Mastra uses built-in exponential backoff to try again. Your workflow will not crash from a simple timeout.

You can configure requireToolApproval for any sensitive tools. The agent will pause and wait for your go-ahead before proceeding with the workflow.

Run the list_protected_applications tool. It returns the application names, protection types, and masked API keys for your mobile and web properties.

Vinkius executes this MCP Server inside an ephemeral sandbox. Your bot scores, origin IPs, and custom rule criteria never hit a database. Everything vanishes the moment the workflow finishes executing.

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