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 Pydantic AI 10 tools — connect in under 2 minutes

Name: Tenable
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Tenable through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Tenable "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Tenable?"
    )
    print(result.data)

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.

Pydantic AI validates every Tenable tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

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 Pydantic AI 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 Pydantic AI via MCP

Follow these steps to integrate the Tenable MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Tenable with type-safe schemas

Why Use Pydantic AI with the Tenable MCP Server

Pydantic AI provides unique advantages when paired with Tenable through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Tenable integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Tenable connection logic from agent behavior for testable, maintainable code

Tenable + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Tenable MCP Server delivers measurable value.

Type-safe data pipelines: query Tenable with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Tenable tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Tenable and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Tenable responses and write comprehensive agent tests

Tenable MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Tenable to Pydantic AI 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 Pydantic AI

Ready-to-use prompts you can give your Pydantic AI 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 Pydantic AI

Common issues when connecting Tenable to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Tenable + Pydantic AI FAQ

Common questions about integrating Tenable MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Tenable MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.