Equixly MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Equixly through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Equixly Assistant",
instructions=(
"You help users interact with Equixly. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Equixly"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Equixly MCP Server
Connect your Equixly account to any AI agent and take full control of your autonomous API security testing and vulnerability management through natural conversation.
The OpenAI Agents SDK auto-discovers all 10 tools from Equixly through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Equixly, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Autonomous Pentest Orchestration — Launch new attack sessions where the Equixly AI Hacker autonomously explores and attacks your API for BOLA, IDOR, and injection flaws
- Service Management — Register and manage target API services by defining base URLs and granular path-scoping rules for continuous monitoring
- API Surface Discovery — Upload and manage API specifications (OpenAPI, GraphQL, Postman) to broaden the attack surface known to the AI Hacker
- Vulnerability Auditing — Retrieve detailed lists of confirmed exploitable security flaws with severity ratings, OWASP mapping, and remediation guidance
- Scan Status Monitoring — Track execution progress and overall outcomes of active penetration tests, including total requests and endpoints explored
- Remediation Oversight — Access evidence of exploitation for specific findings to validate security fixes and maintain production safety
- Target Configuration — Fetch granular metadata for API targets, including authentication hooks and production safety toggles natively
The Equixly MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Equixly to OpenAI Agents SDK via MCP
Follow these steps to integrate the Equixly MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Equixly
Why Use OpenAI Agents SDK with the Equixly MCP Server
OpenAI Agents SDK provides unique advantages when paired with Equixly through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Equixly + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Equixly MCP Server delivers measurable value.
Automated workflows: build agents that query Equixly, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Equixly, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Equixly tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Equixly to resolve tickets, look up records, and update statuses without human intervention
Equixly MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Equixly to OpenAI Agents SDK via MCP:
create_service
Provide the human-readable name and the live base URL. After creation, upload an API spec to maximize attack surface coverage. Register a new API target service for autonomous pentesting
delete_service
Use when decommissioning an API or cleaning up test environments. This action is irreversible. Remove an API service and all its scan history from Equixly
get_scan
Includes total requests made, endpoints explored, attack vectors attempted, severity breakdown of findings (critical/high/medium/low), and OWASP Top 10 mapping. Get detailed status and summary of a specific pentest scan
get_scan_findings
Each finding includes a severity rating, OWASP category, affected endpoint path, HTTP method, request/response evidence of exploitation, and actionable remediation guidance. Download all exploitable vulnerabilities found in a pentest scan
get_service
Required before modifying scan behavior. Get detailed configuration of a specific API service
list_api_specs
The AI Hacker uses these specs to understand the full attack surface, so keeping them updated maximizes vulnerability discovery coverage. List uploaded API specifications for a service
list_scans
Each scan entry includes its status (running, completed, failed), timestamps, and the total count of vulnerabilities detected in that session. List all pentest scan sessions for an API service
list_services
A Service represents a single API base URL that the autonomous AI pentester continuously attacks. Each service contains its unique ID, name, base URL, and the number of discovered endpoints. List all registered API services in Equixly
trigger_scan
It tests for BOLA, broken authentication, mass assignment, IDOR, injection, and business logic flaws. Ideal for CI/CD pipeline integration upon each deployment. Launch a new autonomous AI penetration test against a service
upload_api_spec
Supported formats: openapi (JSON/YAML), postman, graphql, wsdl, har. Pass the raw spec content as a string along with the format identifier. Upload an API specification (OpenAPI, Postman, etc.) to a service
Example Prompts for Equixly in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Equixly immediately.
"Trigger a security scan for API service 'Billing-v1'"
"Show me the critical findings from the latest scan of service 'Payments'"
"List all registered API target services"
Troubleshooting Equixly MCP Server with OpenAI Agents SDK
Common issues when connecting Equixly to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Equixly + OpenAI Agents SDK FAQ
Common questions about integrating Equixly MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Equixly with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Equixly to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.