Ask Your Attack Surface: Connecting Your CTEM Data to an AI Agent via MCP

"What's our most dangerous vulnerability right now?" "Which hosts appeared last week?" You can put questions like these to an AI in plain language and get an answer back, without opening the dashboard and clicking through screens. Those answers are grounded in your own latest attack-surface data.

PentaTrail's CTEM (Continuous Threat Exposure Management) data can now be queried directly from an AI agent. This article covers how it works, what you can do with it, and why it's safe to use.

Connecting your CTEM data to an AI agent

The key is MCP (Model Context Protocol). MCP is an open standard Anthropic published in 2024: a common "socket" that connects AI applications to external data and tools. Major AI vendors have adopted it one after another, and it's becoming the de facto standard for AI integration.

PentaTrail runs a remote MCP server. Register its URL with your AI agent (Claude Code, Claude Desktop, and so on), approve it in the browser, and it connects to your CTEM data with no integration code to write. What used to require "read the API spec, implement auth, write code to parse the responses" now takes one endpoint and one approval.

Here's how you can use it

Once connected, you just ask, in natural language.

• Ad-hoc questions: "Show me the top 5 unaddressed vulnerabilities," "Which new hosts haven't been validated yet?" Staff who don't know a query language, or short-term external members, can reach the information they need right away.
• Summarizing the situation: Ask "summarize this week's new detections and resolutions," and the AI reads across your data to summarize it. For how priority is set, see TER bands and TDL.
• Drafting reports: Board or parent-company reports follow nearly the same structure every week. Have the AI pull the numbers and draft it, and your staff can focus on comments and review.

Built to use with confidence

You're connecting your own security data to an AI, so it should be handled carefully. PentaTrail applies exactly the same protections to access via an AI agent as to normal use.

• You only ever see your own contract's data: every request is bound to your contract, and other organizations' data is completely out of reach (row-level security).
• No secret is kept on your side: the connection is established by an approval in the browser, so no credential goes into your tool's configuration. Approval can be revoked at any time from the admin console, and a revoked tool can read nothing.
• Calls are capped: too many calls in a short window are turned away, with the time you can resume.

Getting started

Connecting is simple.

1. Register https://api.pentatrail.co/mcp with your AI agent as a remote server.
2. Your browser opens when the tool connects — read what that connection can do, then approve it.
3. Ask: "Tell me the top vulnerabilities for our domain."

The tools, and the failures they return, are documented in the MCP server guide.

The value of CTEM lies in grasping your attack surface continuously. Being able to ask about that ongoing picture in plain language, before you even open the dashboard, makes the entry point to operations much lighter.

To make your attack surface askable by AI, start your 14-day free trial. For the bigger picture of CTEM, see What is CTEM?