How do I configure my credentials for Rapid7?

The integration uses Basic Authentication interacting with the Rapid7 Console API. You must configure the `RAPID7_HOST` (IP or FQDN), `RAPID7_PORT` (usually 3780), along with a dedicated `RAPID7_USER` and `RAPID7_PASSWORD`. We strongly recommend generating a specific service account in your console with restricted scan permissions.

Is the scanning triggered individually per asset?

By default, the `trigger_scan` mechanism relies on referencing a defined `site_id`, scanning the preconfigured scope attached to it rather than blindly scanning one unassociated IP.

Does it report CVSS scores?

Yes, depending on the response data provided by your installed version of the InsightVM console. Using `get_vulnerability` or checking asset lists brings standard threat metadata and corresponding CVSS vectors directly into your AI interface context.

Rapid7 InsightVM MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Rapid7 InsightVM
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 Rapid7 InsightVM through the 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 Rapid7 InsightVM "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Rapid7 InsightVM?"
    )
    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 Rapid7 InsightVM MCP Server

Connect your Rapid7 InsightVM (formerly Nexpose) platform directly to your AI agent. By granting this access, your AI becomes a highly interactive cybersecurity assistant, allowing engineers and security analysts to query vulnerabilities, review asset health, and start scans right from their workspace or IDE.

Pydantic AI validates every Rapid7 InsightVM tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the 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

Asset Querying — Retrieve comprehensive inventory lists to discover all tracked computing assets and read their operating system fingerprints and hardware information.
Vulnerability Checks — Scan specific assets to instantly read CVE numbers mapped against them, alongside full vulnerability advisories and remediation guidelines.
Scan Operations — Read chronologically maintained assessment scans and track their execution status without jumping between consoles.
Site Management — Explore configured network sites, observing their designated scanning scopes and reviewing overall health risks.
Trigger Scanning — Force an immediate re-evaluation scan on a specified site after applying a patch, validating your resolution securely.

The Rapid7 InsightVM 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 Rapid7 InsightVM to Pydantic AI via MCP

Follow these steps to integrate the Rapid7 InsightVM 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 Rapid7 InsightVM with type-safe schemas

Why Use Pydantic AI with the Rapid7 InsightVM MCP Server

Pydantic AI provides unique advantages when paired with Rapid7 InsightVM 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 Rapid7 InsightVM integration code

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

Dependency injection system cleanly separates your Rapid7 InsightVM connection logic from agent behavior for testable, maintainable code

Rapid7 InsightVM + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Rapid7 InsightVM MCP Server delivers measurable value.

Type-safe data pipelines: query Rapid7 InsightVM with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Rapid7 InsightVM tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Rapid7 InsightVM and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Rapid7 InsightVM responses and write comprehensive agent tests

Rapid7 InsightVM MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Rapid7 InsightVM to Pydantic AI via MCP:

get_asset

Retrieves detailed information for a specific asset

get_asset_vulnerabilities

Lists all vulnerabilities found on a specific asset

get_scan

Retrieves execution status and results for a specific scan

get_site

Retrieves details for a specific network site

get_vulnerability

Retrieves details for a specific vulnerability ID

list_assets

Lists all discovered computing assets

list_scans

Lists chronological assessment scans

list_sites

Lists all configured network scan sites

list_vulnerabilities

Lists global vulnerability definitions

trigger_scan

Forces an immediate vulnerability scan for a site

Example Prompts for Rapid7 InsightVM in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Rapid7 InsightVM immediately.

"Fetch the list of network sites currently managed by Rapid7."

"What vulnerabilities are discovered on asset 1052?"

"Force a new scan on Site ID 15 immediately."

Troubleshooting Rapid7 InsightVM MCP Server with Pydantic AI

Common issues when connecting Rapid7 InsightVM to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Rapid7 InsightVM + Pydantic AI FAQ

Common questions about integrating Rapid7 InsightVM 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 Rapid7 InsightVM MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.