Riskscore MCP Server

@ItIsCuthNotCup

Basic information

About Riskscore MCP Server

Security awareness for AI agents — so your agent knows what's dangerous before it acts. Powered by CVE, NVD, CISA KEV, and OSV.dev vulnerability data with 196 credential detection rules, returning allow/warn/block decisions in real time. Stop your agent from running vulnerable de

#security #cve #vulnerability #ai-agent #mcp

Riskscore MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "riskscore": {
      "command": "python",
      "args": [
        "mcp/server.py"
      ],
      "env": {
        "RISKSCORE_API_KEY": "your_key_here",
        "RISKSCORE_BASE_URL": "https://riskscore2.p.rapidapi.com"
      }
    }
  }
}

Riskscore MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Riskscore?

Riskscore provides security awareness for AI agents by checking actions against vulnerability data from CVE, NVD, CISA KEV, and OSV.dev, along with 196 credential detection rules. It returns allow, warn, or block decisions in real time, helping agents avoid running vulnerable dependencies, leaking secrets, or accidentally deleting files.

How to use Riskscore?

The README does not provide installation or configuration instructions. Invoke Riskscore to evaluate an agent’s intended action and receive an allow/warn/block decision based on current vulnerability and credential data.

Key features of Riskscore

Real-time allow, warn, or block decisions.
Powered by CVE, NVD, CISA KEV, and OSV.dev data.
196 credential detection rules for secret leakage.
Focused on AI agent safety and proactive risk awareness.

Use cases of Riskscore

Prevent an AI agent from executing a command that uses a known vulnerable dependency.
Block an agent from accidentally committing or sending a detected credential or secret.
Warn an agent before it attempts to delete critical filesystem paths.
Scan agent actions against the latest CISA Known Exploited Vulnerabilities catalog.

Frequently asked questions

What vulnerability sources does Riskscore use?

Riskscore uses data from CVE, NVD, CISA KEV, and OSV.dev.

How does Riskscore protect against secrets?

It includes 196 credential detection rules to identify and block potential secret leakage.

What kind of decisions can Riskscore return?

Riskscore returns one of three decisions: allow, warn, or block.

Who is Riskscore designed for?

Riskscore is designed for AI agents and developers who want to embed security awareness directly into agent workflows.

Does Riskscore require any runtime dependencies?

The README does not list any specific runtime or dependency requirements.

Comments

More Developer Tools MCP servers

Raccha AI

Shree Mandadi

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a

Official Porkbun MCP Server

Porkbun LLC

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools