CSF Tools Now Speaks MCP

CSF Tools featured image for New Tools for Agents: a colored CSF function wheel connected to an AI agent icon.

CSF Tools has always been a human-readable map of security frameworks and controls. It now exposes that same library over the Model Context Protocol (MCP), so an AI agent can look up a control, follow its mappings, and answer questions without scraping pages.

Example questions that should work once you are connected:

  • What does NIST SP 800-53 Rev. 5 AC-2 require, and which CSF 2.0 subcategories does it support?
  • Crosswalk CIS Controls 8.1 to NIST 800-53 and the Privacy Framework.
  • Which STRIDE-LM threats does NIST 800-53 Control CP-7 address?
  • Show the High baseline enhancements for SC-7.

What you need

  1. Create an account at CSF Tools. Check email for the confirmation.
  2. Next, go to “API Access” under the profile menu and create an application password.
    Demonstration of the user profile menu with API Access option highlighted.
    You will see a one-time display of the password.
    Application password one-time display.
  3. Point your MCP client at: https://csf.tools/wp-json/csftools/v1/mcp

Authenticate with HTTP Basic Auth:

  • Username: your CSF Tools username
  • Password: the application password

If the client only accepts a header, send:

Authorization: Basic <base64 of username:application-password>

Claude Desktop example:

{
  "mcpServers": {
    "csf-tools": {
      "url": "https://csf.tools/wp-json/csftools/v1/mcp",
      "headers": {
        "Authorization": "Basic REPLACE_ME"
      }
    }
  }
}

Access is read-only. Create one application password per client and revoke it from your profile if you stop using that client. Never put your login password in an agent config.

NIST Releases Version 2 of the Cybersecurity Framework (CSF)

NIST CSF v2.0

On February 26, 2024, NIST released version 2 of the Cybersecurity Framework (CSF). The new version makes some significant changes, such as moving Governance out of the Identify function and into its own dedicated Govern function.

Control mappings and references to version 2 are still being developed and released. As they come out, we will continue to update this site with tools to make the most of the framework.

Click here to go to the Cybersecurity Framework Version 2.

Using the STRIDE-LM Threat Model to Drive Security Control Selection

Contour map with threat icons leading to a control icon.

Using threat modeling can be an effective way to prioritize security control implementation efforts for a given solution. The resulting prioritization can then be used to help optimize time or financial costs during solution development. The following is a brief overview of using the threat modeling process to select both NIST CSF security outcomes and NIST security controls.

Continue reading “Using the STRIDE-LM Threat Model to Drive Security Control Selection”

Welcome!

Welcome to CSF Tools! You may be wondering what all this stuff is and why I put it here. Like so many things in life as a technologist, this all started with me trying to find ways to visualize the NIST Cybersecurity Framework for a PowerPoint presentation. I wasn’t really happy with the stuff I found, so decided to start building a library of visualizations linking that CSF to different control sets.

What is here so far is just the beginning. I have many ideas regarding new visualizations, control sets, and features to increase flexibility of presentation. Check back in periodically — you never know what you might find!