How do I connect my Rapid7 console to this MCP?

You need to provide the URL and port of your Rapid7 Security Console along with credentials configured for Basic Authentication.

Can I start a scan through my AI client?

Yes, you can use the trigger_scan capability to force an immediate vulnerability scan on a specific site.

What kind of asset data can my agent see?

Your agent can access discovered computing assets, including their operating system fingerprints and hardware information.

Does this work with Nexpose?

Yes, this MCP works with the Rapid7 InsightVM platform, which is the successor to Nexpose.

Can I check if a specific CVE is present on a host?

Yes, you can ask your agent to list vulnerabilities for a specific asset to see mapped CVE numbers and advisories.

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.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Rapid7 InsightVM to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage vulnerabilities and trigger scans without leaving your workspace.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Rapid7 InsightVM.

01
List assets
This capability pulls a complete list of all computing assets discovered in your environment.
02
List vulnerabilities
Use this to get a list of all global vulnerability definitions currently tracked.
03
Get scan
This capability retrieves the specific results and current execution status for a single scan.
04
Get asset
Get detailed technical information for a specific asset through this capability.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Rapid7 InsightVM.

05
Get asset vulnerabilities
This capability lists every vulnerability found on a specific host.
06
Get site
Use this to pull configuration and detail for a specific network site.
07
Get vulnerability
This capability retrieves the full details for a specific vulnerability ID.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Rapid7 InsightVM.

08
List scans
Get a chronological list of all assessment scans performed.
09
List sites
This capability provides a list of all configured network scan sites.
10
Trigger scan
Force an immediate vulnerability scan on a designated site using this capability.

Real work

What teams actually run

Post-Patch Validation

After applying an OS update, you tell your agent to trigger a scan on that subnet to confirm the vulnerability is gone.

Rapid Incident Response

When a new CVE is announced, you ask your agent to find all assets currently affected by that specific ID.

Network Provisioning

New subnets can be audited immediately by having your agent check the site configuration and scan scope.

Inventory Audits

You can pull a complete list of all tracked computing assets and their hardware info in seconds.

Automate a task

Put Rapid7 InsightVM to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Rapid7 InsightVM works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Rapid7 InsightVM to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

913ms average. Fast in production.

Rapid7 InsightVM is checked daily against the live service.

Daily averagePeak 1190ms

Oct 3Today

Fastest day: 774ms
Slowest day: 1190ms
14-day trend: Slowing+11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Rapid7 InsightVM, so you can see the experience inside your AI.

It does not authenticate your account with Rapid7 InsightVM. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Rapid7 InsightVM Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_nmw1NBAd0c7vaxJkPlmlyGDkr9YvNNJBYZZGurqi/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Rapid7 InsightVM capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "rapid7-insightvm-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_nmw1NBAd0c7vaxJkPlmlyGDkr9YvNNJBYZZGurqi/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Rapid7 InsightVM in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Rapid7 InsightVM owners hand off.

This MCP is built for technical teams who need to move quickly between security analysis and system administration.

01
Cybersecurity Analysts
They use the agent to fetch CVE details and remediation steps during incident response.
02
DevOps Engineers
They trigger scans on subnets to verify that patches were applied correctly.
03
Network Engineers
They check site configurations and scanning scopes when provisioning new subnets.

FAQ

Questions Rapid7 InsightVM owners ask.

01
How do I connect my Rapid7 console to this MCP?
You need to provide the URL and port of your Rapid7 Security Console along with credentials configured for Basic Authentication.
02
Can I start a scan through my AI client?
Yes, you can use the trigger_scan capability to force an immediate vulnerability scan on a specific site.
03
What kind of asset data can my agent see?
Your agent can access discovered computing assets, including their operating system fingerprints and hardware information.
04
Does this work with Nexpose?
Yes, this MCP works with the Rapid7 InsightVM platform, which is the successor to Nexpose.
05
Can I check if a specific CVE is present on a host?
Yes, you can ask your agent to list vulnerabilities for a specific asset to see mapped CVE numbers and advisories.
06
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.
07
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.
08
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.

Explore

More in Fort Knox

Connect Rapid7 InsightVM to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List assets

List vulnerabilities

Get scan

Get asset

05-07

Get asset vulnerabilities

Get site

Get vulnerability

08-10

List scans

List sites

Trigger scan

What teams actually run

Post-Patch Validation

Rapid Incident Response

Network Provisioning

Inventory Audits

Building your own app? The connector is yours to use.

Rapid7 InsightVM Connector

Claude Desktop

Cybersecurity Analysts

DevOps Engineers

Network Engineers

How do I connect my Rapid7 console to this MCP?

Can I start a scan through my AI client?

What kind of asset data can my agent see?

Does this work with Nexpose?

Can I check if a specific CVE is present on a host?

How do I configure my credentials for Rapid7?

Is the scanning triggered individually per asset?

Does it report CVSS scores?

Halo Security AI Connector

Lacework (Cloud Security & CNAPP) AI Connector

Cisco Meraki AI Connector

Trend Micro AI Connector

Suggestions

Home Network Device Inventory AI Connector

Security Audit Prover AI Connector

Asset Panda AI Connector

Nmap Online AI Connector