mcpField
C
CVSS Calculator MCP

CVSS Calculator MCP

Remote
github.com/alfa-rezaSecurity2Updated 1d ago
Repository

About CVSS Calculator MCP

CVSS Calculator MCP is a Go-based MCP server for AI agents that calculates and validates CVSS base scores across versions 2.0, 3.0, 3.1, and 4.0. It supports both local stdio and remote Streamable HTTP connections.

Key features

  1. 01CVSS 2.0, 3.0, 3.1, and 4.0 scoring
  2. 02Base vector validation
  3. 03Local stdio transport
  4. 04Remote Streamable HTTP transport

Use cases

  1. 01Calculate a score from a complete CVSS base vector
  2. 02Validate base vectors across CVSS versions

MCP support

Exposes the `calculate_cvss` tool to MCP clients, accepting a version and vector and returning a score and severity. It can run over stdio locally or Streamable HTTP remotely.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://cvss.my.id/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

CVSS Calculator MCP

A lightweight CVSS Base Score calculator for AI agents, built with Go.

Version 1.0.0 Go version CI status License MCP

Website · MCP Registry · LobeHub · Glama Server · Glama Connector

Calculate and validate CVSS 2.0, 3.0, 3.1, and 4.0 Base Scores through a single MCP tool: calculate_cvss. Supports local stdio and remote Streamable HTTP.

Quick Start

Option 1 — Install Locally

Linux / macOS:

curl -fsSL https://get.cvss.my.id/install.sh | bash

Add the installed binary to your MCP client (choose one):

# Claude Code
claude mcp add --scope user cvss-calculator -- cvss-calculator-mcp

# Codex
codex mcp add cvss-calculator -- cvss-calculator-mcp

# OpenCode v2
opencode mcp add cvss-calculator --global -- cvss-calculator-mcp

Also available via GitHub Releases (including Windows) or go install github.com/alfa-reza/cvss-calculator-mcp/cmd/cvss-calculator-mcp@latest (Go 1.25+). Ensure the binary is in your PATH.

Option 2 — Free Remote MCP

No installation or API key required. Connect to https://cvss.my.id/mcp:

# Claude Code
claude mcp add --scope user --transport http cvss-calculator https://cvss.my.id/mcp

# Codex
codex mcp add cvss-calculator --url https://cvss.my.id/mcp

# OpenCode v2
opencode mcp add cvss-calculator --global --url https://cvss.my.id/mcp

Rate limit: 5 requests per minute per IP address. Use the local option to avoid this shared-service limit.

Other MCP clients (Cursor, Claude Desktop, VS Code, etc.)

Use cvss-calculator-mcp as a local stdio command, or https://cvss.my.id/mcp as a remote Streamable HTTP endpoint. Configuration formats depend on the client.

Cursor / Claude Desktop — local configuration (mcpServers):

{
  "mcpServers": {
    "cvss-calculator": { "command": "cvss-calculator-mcp" }
  }
}

For Cursor remote, use "url": "https://cvss.my.id/mcp" instead of the command entry.

VS Code — remote configuration (.vscode/mcp.json):

{
  "servers": {
    "cvss-calculator": { "type": "http", "url": "https://cvss.my.id/mcp" }
  }
}

See the client documentation for configuration locations and setup: Cursor · Claude Desktop · VS Code.

Usage

Ask your connected AI assistant:

Calculate the CVSS 3.1 Base Score for CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

The calculate_cvss tool accepts version and vector, returning a score and severity (for this example, 9.8 — Critical). Only complete Base vectors are supported; no CVE lookups or vulnerability scanning.

Self-Hosting

The Go binary uses stdio by default. For Streamable HTTP, run cvss-calculator-mcp --transport http (listens on 127.0.0.1:43871/mcp by default; customize with --listen).

License

Apache-2.0. CVSS is maintained by FIRST; this project is independent of FIRST.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.