Can my AI agent trigger vulnerability scans directly?

Yes! You can ask your agent to list all mapped scan profiles. Once you copy the ID for something like 'External Perimeter Quick Scan', you can tell the agent to seamlessly launch that specific scan ID out of standard bounds.

How easy is it to investigate an alert about a single compromised asset?

Extremely fast. If an IP triggers an alert downstream, ask your agent to retrieve asset details tracking that IP, obtain its specific Asset ID, and immediately pull vulnerabilities. You will instantly get a markdown table of CVEs missing on the endpoint without complex GUI clicking.

Can the agent interact with scanner appliances (Nessus)?

Yes. It can fetch your entire scanner inventory across Tenable.io. This includes the internal Nessus agents linked to the account, their connection status, license states, and underlying software versions so you know if your fleet is healthy.

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

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

        result = await Runner.run(
            agent, "List all available tools from Tenable"
        )
        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 Tenable MCP Server

Connect your Tenable (Tenable.io) environment to any AI agent and bring your enterprise vulnerability management directly into your IDE or chat via natural conversation.

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

What you can do

Scans & Assessments — List configured vulnerability scans, retrieve detailed run analytics, and even manually trigger immediate evaluations
Asset Intelligence — Browse your entire host and cloud inventory, retrieving deep telemetry like OS fingerprints, IPs, and tags
Vulnerability Triage — Pinpoint explicit security findings (Workbench) and CVEs affecting specific assets without navigating complex dashboards
Topology Oversight — See how your network spaces overlap and track organizational logical folders
Scanner Health — Check the operational status and plugin health of your internal enterprise scanning fleet

The Tenable 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 Tenable to OpenAI Agents SDK via MCP

Follow these steps to integrate the Tenable 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 Tenable

Why Use OpenAI Agents SDK with the Tenable MCP Server

OpenAI Agents SDK provides unique advantages when paired with Tenable 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

Tenable + OpenAI Agents SDK Use Cases

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

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

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

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

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

Tenable MCP Tools for OpenAI Agents SDK (10)

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

get_asset_details

Retrieves detailed metadata, networking, and risk profile for a specific asset

get_asset_vulnerabilities

Retrieves explicit security findings (Workbench) for a specific asset

get_scan_results

Retrieves runtime analytics and vulnerability summaries for a specific scan

launch_scan

Returns the newly created scan run ID. Manually triggers an immediate execution of a configured scan

list_asset_tags

g. "Critical", "Production", "External"). Lists organizational tags mapped to assets

list_assets

Lists host and cloud assets discovered in Tenable.io

list_logical_networks

Lists Tenable logical routing networks

list_scan_folders

g. "My Scans", "PCI Quarters"). Lists operational scan folders

list_scanners

Lists Nessus scanners managed by Tenable.io

list_scans

Lists vulnerability assessment scans from Tenable.io

Example Prompts for Tenable in OpenAI Agents SDK

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

"Find the status and schedule of the 'Weekly PCI Scan'."

"Retrieve all extreme vulnerabilities on asset ID 1383da-xxx."

"Launch the scan with ID a981bf93 immediately."

Troubleshooting Tenable MCP Server with OpenAI Agents SDK

Common issues when connecting Tenable 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.

Tenable + OpenAI Agents SDK FAQ

Common questions about integrating Tenable 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.