Cortex XSIAM MCP Server for OpenAI Agents SDK 9 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Cortex XSIAM 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="Cortex XSIAM Assistant",
instructions=(
"You help users interact with Cortex XSIAM. "
"You have access to 9 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Cortex XSIAM"
)
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 Cortex XSIAM MCP Server
Connect Cortex XSIAM to any AI agent via MCP.
How to Connect Cortex XSIAM to OpenAI Agents SDK via MCP
Follow these steps to integrate the Cortex XSIAM 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 9 tools from Cortex XSIAM
Why Use OpenAI Agents SDK with the Cortex XSIAM MCP Server
OpenAI Agents SDK provides unique advantages when paired with Cortex XSIAM 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
Cortex XSIAM + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Cortex XSIAM MCP Server delivers measurable value.
Automated workflows: build agents that query Cortex XSIAM, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Cortex XSIAM, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Cortex XSIAM tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Cortex XSIAM to resolve tickets, look up records, and update statuses without human intervention
Cortex XSIAM MCP Tools for OpenAI Agents SDK (9)
These 9 tools become available when you connect Cortex XSIAM to OpenAI Agents SDK via MCP:
execute_playbook
g., enrich IOCs, block IP, reset password). Requires playbook name and optional input arguments. Use this to speed up response times and ensure consistent handling of incidents. Execute an automated incident response playbook in Cortex XSIAM
get_alerts
Use this to review detection rules firing or analyze threat patterns. List security alerts detected by Cortex XSIAM
get_endpoints
Use this to audit endpoint coverage, identify disconnected hosts, or target remediation actions. List managed endpoints (hosts/devices) in Cortex XSIAM
get_incident_details
Requires the incident ID. Use this for deep investigation or context before taking action. Get detailed information about a specific security incident
get_incidents
Use this to monitor SOC queue, identify high-severity incidents, or track analyst workload. Supports sorting and limiting results. List security incidents in Cortex XSIAM
get_indicators
Use this to review threat intelligence or check if specific artifacts are known malicious. List indicators of compromise (IOCs) tracked in Cortex XSIAM
isolate_endpoint
Requires the endpoint ID. Use this immediately upon confirming a severe compromise to prevent lateral movement. Isolate a compromised endpoint from the network
run_xql_query
XQL allows searching logs, endpoints, network data, and more. Requires a valid XQL query string. Returns the results of the query. Use this for custom threat hunting, compliance reporting, or data analysis. Execute an XQL (Cortex Query Language) query for advanced threat hunting
scan_endpoint
Supports "quick" or "deep" scan types. Requires the endpoint ID. Use this to verify if a host is infected or after cleaning a threat. Trigger a malware scan on a specific endpoint
Troubleshooting Cortex XSIAM MCP Server with OpenAI Agents SDK
Common issues when connecting Cortex XSIAM to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Cortex XSIAM + OpenAI Agents SDK FAQ
Common questions about integrating Cortex XSIAM 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 Cortex XSIAM 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 Cortex XSIAM to OpenAI Agents SDK
Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.