How to Use the Equixly MCP in OpenAI Agents SDK

Q: Can I run an Equixly scan asynchronously within an OpenAI Agents SDK loop?

Yes. You launch the run with triggerscan and have your agent poll getscan periodically over the MCP connection to check execution status.

Q: How do I register new API targets using Equixly and OpenAI Agents SDK over MCP?

Use the createservice tool to register the base URL. Once registered, your agent can immediately upload the API specification to begin scanning.

Run autonomous API security testing directly inside your production OpenAI Agents SDK pipelines to catch vulnerabilities before they hit prod.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equixly MCP to OpenAI Agents SDK

Create your Vinkius account to connect Equixly 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 Equixly with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run pentests inside OpenAI Agents SDK workflows

The `trigger_scan` tool lets your agent launch an autonomous security assessment against your API targets to find critical flaws like BOLA and IDOR. It executes attacks against the base URL and reports back once the run is complete. You don't have to manually configure attack vectors. The agent handles the execution queue over the MCP Server connection, and you can fetch the final status using `get_scan` to verify if the endpoints withstood the simulated exploit attempts.

Sync API schemas for targeted agent attacks

The `upload_api_spec` tool feeds your OpenAPI or Postman collections directly to the scanner so the agent knows exactly where to direct its probes. This ensures the automated attacker maps out every single route instead of guessing. Keeping these definitions fresh is simple. Your agent can call `list_api_specs` to check current versions, matching the spec to the active code branch during automated CI runs.

Extract actionable exploit evidence via MCP Server

The `get_scan_findings` tool pulls down raw evidence of exploitation, including HTTP requests and responses, for any vulnerability discovered. Your python agents can parse this data to auto-assign tickets or block deployments. To keep your environment clean, you can manage targets on the fly. The agent can query `list_services` to inventory your active APIs or run `delete_service` to wipe out retired endpoints and their historical logs.

Setup guide

Set up Equixly 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 Equixly tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Equixly 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="Equixly Agent",
            instructions="You have access to Equixly 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 Equixly. 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 Equixly 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 Equixly MCP in OpenAI Agents SDK

The SDK automatically discovers all 10 tools when you register the server endpoint. Your agent reads the tool schemas and invokes them dynamically during execution.

Yes. You launch the run with `trigger_scan` and have your agent poll `get_scan` periodically over the MCP connection to check execution status.

Use the `create_service` tool to register the base URL. Once registered, your agent can immediately upload the API specification to begin scanning.

The server accepts OpenAPI JSON or YAML, Postman collections, GraphQL schemas, WSDL, and HAR files. Pass the raw string to the upload tool.

Your API specifications and vulnerability reports are processed in secure, isolated sandboxes. The server only holds active target definitions and scan results required to generate remediation steps, ensuring your endpoint schemas remain protected.

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