How can the AI help me fix a vulnerability faster?

Once an issue is identified via scan results, ask your agent to pull the 'Best Fix Location' (BFL) using the query ID. Checkmarx mathematically finds the common root code block, and your AI can instantly rewrite that exact block to sanitize the flaw. You save hours tracing code paths.

Can the agent initiate a static code scan independently?

Yes! Tell the agent to 'Run a scan on project ID X targeting the main branch'. It initiates the analysis array natively across Checkmarx One engines. You can poll for completion status later and retrieve the new dataset directly via chat.

Does it segregate AppSec results from Cloud infrastructure flaws?

It does. Application flaws are pulled cleanly via `get_scan_results`, whereas misconfigurations tied to Docker, Kubernetes, or Terraform limits use a dedicated `get_kics_results` pipeline. The agent intrinsically separates the context for your DevOps team.

Checkmarx MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Checkmarx
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Checkmarx through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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="Checkmarx Assistant",
            instructions=(
                "You help users interact with Checkmarx. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Checkmarx"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Checkmarx MCP Server

Connect your Checkmarx One enterprise environment to any AI agent and take programmatic control over your Application Security posture. Analyze deep code flaws through natural chat instead of navigating complex cyber dashboards.

The OpenAI Agents SDK auto-discovers all 10 tools from Checkmarx through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Checkmarx, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Projects & Applications — Inventory your codebase containers, inspect active project linkages, and prepare specific branches for security scanning
Scans Lifecycle — Trigger dynamic SAST/SCA security scans on repos, cancel redundant queues, and poll engines for precise execution timing
Vulnerability Triage — Extract core datasets of severe vulnerabilities, mapping exact lines of code where the flawed logic resides
Best Fix Location (BFL) — Ask the agent to calculate the exact optimal spot in your execution path to apply a patch that resolves the flaw entirely
KICS (IaC) — Read specialized Infrastructure as Code metrics isolating misconfigurations exclusively in Terraform, Dockerfiles, or Kubernetes YAML

The Checkmarx 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 Checkmarx to OpenAI Agents SDK via MCP

Follow these steps to integrate the Checkmarx 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 Checkmarx

Why Use OpenAI Agents SDK with the Checkmarx MCP Server

OpenAI Agents SDK provides unique advantages when paired with Checkmarx 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

Checkmarx + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Checkmarx MCP Server delivers measurable value.

Automated workflows: build agents that query Checkmarx, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Checkmarx, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Checkmarx tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Checkmarx to resolve tickets, look up records, and update statuses without human intervention

Checkmarx MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Checkmarx to OpenAI Agents SDK via MCP:

cancel_scan

Prevents unnecessary engine resource consumption and drops the scanning context if the developer pushed a new commit overlapping the running job. Cancel an actively running Checkmarx scan

get_kics_results

Focuses solely on Terraform, CloudFormation, Kubernetes YAML, and Dockerfile misconfigurations rather than typical application source code flaws. Get specialized Infrastructure as Code (KICS) findings

get_project

Essential for ensuring the correct branch and source control context is selected before triggering new scans. Get details for a specific Checkmarx project

get_scan_details

It returns granular execution details including which scan engines (SAST, SCA, KICS) were fired, their individual execution timings, and any engine-specific failure reasons. Check the precise status and configuration of a Checkmarx scan

get_scan_results

Each result includes the vulnerability severity, state (To Verify, Confirmed, Urgent), description, and the exact lines of code where the flaw was detected. Requires a completed scan ID. Download SAST and security vulnerability findings for a scan

list_applications

An Application acts as an overarching container for multiple individual microservices or projects, providing aggregated risk reporting and security metric visibility across a logical product. List Checkmarx One Applications

list_bfl

Provide the scan ID and the specific query (rule) ID string. Get Best Fix Location (BFL) for a specific vulnerability node

list_projects

A Project represents a specific codebase. Includes project metadata, IDs, and assigned application linkages. List all Checkmarx One Projects

list_scans

Includes the scan ID, current status (Completed, Running, Failed, Canceled), branch targeted, and timestamps. Use the scan ID to fetch the actual vulnerability results. List all historical and active scans for a Checkmarx project

run_scan

Extensively used in CI/CD integrations to assert security quality on PRs. Returns the ID of the newly queued scan. Trigger a new Checkmarx One code scan

Example Prompts for Checkmarx in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Checkmarx immediately.

"List the most severe vulnerabilities found in the last Checkmarx scan."

"Trigger a new SAST scan for my current Checkmarx project."

"How do I fix the SQL injection vulnerability found in the Checkmarx report?"

Troubleshooting Checkmarx MCP Server with OpenAI Agents SDK

Common issues when connecting Checkmarx to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Checkmarx + OpenAI Agents SDK FAQ

Common questions about integrating Checkmarx MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.