How to Use the DataDome MCP in OpenAI Agents SDK

Q: How do I connect DataDome to my OpenAI Agents SDK?

Install openai-agents and spin up the MCP Server endpoint. Pass the server URL to MCPServerStreamableHttp and add it to your agent's server list. The SDK automatically discovers all ten tools.

Q: Does this DataDome integration expose raw user IP addresses to OpenAI?

The listaccesslogs tool retrieves IP addresses and geolocation data of incoming requests to analyze threat patterns. All data stays within your local Vinkius MCP sandbox, ensuring no raw client IPs are sent to external model providers unless you explicitly configure your agent to pass them.

Stop guessing if scrapers are hitting your API. Let your OpenAI Agents SDK inspect DataDome bot logs in real time.

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 OpenAI Agents SDK

Create your Vinkius account to connect DataDome to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Live Bot Traffic via OpenAI Agents SDK

The `get_bot_traffic_summary` tool fetches real-time distributions of verified crawlers versus malicious scrapers targeting your application. Your agent uses this metric breakdown to decide whether to trigger automated rate-limiting adjustments or run defensive playbooks. By connecting this MCP Server to your OpenAI agent setup, you give your code the ability to trace traffic spikes instantly. The agent parses the raw ratios, identifies anomalies, and routes the threat data to your security team before your database takes a hit.

Inspect Endpoint Health and Threat Details

The `get_endpoint_health` and `get_threat_details` tools expose operational latency and raw behavioral patterns of blocked requests directly to your agent. When a sudden spike in errors occurs, the agent pulls the exact detection logic that triggered the block. This means your agent can automatically determine if a genuine user got caught in a false positive or if an actual credential stuffing attack is underway. It does this by inspecting request headers and behavioral flags without requiring manual dashboard lookups.

Manage Custom Bot Rules in Real Time

The `list_custom_bot_rules` tool lists active IP, User-Agent, and geographic blocks configured on your edge. Your agent reads these rules to check if a specific malicious IP is already blocked or if a new rule needs to be drafted. Feeding this data directly to your OpenAI agent allows it to verify your active defense configurations against incoming threat intelligence feeds. If a known bad actor matches an existing rule, the agent logs the match and proceeds to the next security task.

Setup guide

Set up DataDome MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all DataDome tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives DataDome tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DataDome tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="DataDome Agent",
            instructions="You have access to DataDome tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and spin up the MCP Server endpoint. Pass the server URL to `MCPServerStreamableHttp` and add it to your agent's server list. The SDK automatically discovers all ten tools.

No, this server currently acts as a monitoring and audit tool. Your agent can read rules using `list_custom_bot_rules` and inspect threats, but it won't write new rules directly to your live production firewall.

The SDK relies on standard HTTP backoff when calling the server. If your agent makes rapid calls to `get_protection_stats`, the server handles the throttling to prevent your API tokens from getting blocked.

Yes, you can configure your agent's tool access at the SDK level. If you only want the agent to monitor health, expose `get_endpoint_health` and hide the raw logs.

The `list_access_logs` tool retrieves IP addresses and geolocation data of incoming requests to analyze threat patterns. All data stays within your local Vinkius MCP sandbox, ensuring no raw client IPs are sent to external model providers unless you explicitly configure your agent to pass them.

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