Find your Reachable Risk. Defer the rest.

CVE prioritization for engineering teams using Claude Code, Codex, or similar AI coding agents. See what to fix today, what to schedule, and what to defer, based on what’s actually being exploited and what reaches exploitable paths in your application.

Real repo. 55 Dependabot alerts. 0 fix today, 0 to schedule, 55 to defer. Watch the 5-minute demo.

Start your 7-day free trial

The Problem with CVE Prioritization Today

NIST stopped independently assessing CVE severity in April 2026. CVE volume is expected to double this year. Your team is left with severity scores that no longer mean anything, and a backlog that grows faster than you can triage it.

Everything looks equally urgent. Nothing gets fixed fast enough.

Reachable Risk: Reachability Analysis Inside Your AI Coding Agent

Reachable Risk plugs directly into the AI coding agent your engineers already use (Claude Code, Codex, similar) and gives it two signals that actually predict exploitability, plus the reachability check the agent is uniquely positioned to do.

  • VulnCheck KEV — known exploited vulnerabilities (real-world attack evidence).
  • FIRST EPSS — exploit prediction scoring (probability of exploitation in the next 30 days).
  • Reachability — the scorer runs inside your coding agent, which weighs each CVE against the code your agent can already read in your repo.

The result is a defensible risk score that knows the difference between a CVE burning down the internet and a CVE that doesn’t reach a single live code path in your app.

In minutes, not weeks. No new dashboard to learn.

What You Get

  • MCP server — connects directly to Claude Code, Codex, or compatible agents via the Model Context Protocol.
  • VulnCheck KEV lookup — real-world exploitation evidence per CVE.
  • FIRST EPSS scoring — 30-day exploit probability per CVE.
  • score_risk MCP tool — agent-callable scoring that combines KEV + EPSS + reachability into a defensible risk score per finding.
  • Reachability-aware scoring — your agent weighs KEV + EPSS against the code it can read in your repo, so “in your app” isn’t generic.
  • Risk scoring rubric — a defensible methodology your auditors will accept, shipped as an MCP prompt resource so the agent applies it directly.
  • Prompt guidance — how to weight KEV + EPSS signals into a final priority score.

What You Do, What We Do: CVE Prioritization Without the Hidden Phase

We do You do
Maintain KEV + EPSS feeds Feed CVE findings from Dependabot, Wiz, Tenable, etc
Score every CVE, in minutes Add the MCP server to your agent (3-line config)
Publish the scoring rubric Apply the prioritized fixes
Update the prompt guidance as feeds change Decide which deferred CVEs to revisit, and when

No surprise work. No hidden integration phase.

Why This, Why Now

The AI-generated vulnerability tsunami is already here. In May 2026, the maintainer of dnsmasq (software running on hundreds of millions of devices) disclosed 6 CVEs in a single day, all discovered by AI-based security research tools. His words:

There has been something of a revolution in AI-based security research. The tsunami of AI-generated bug reports shows no signs of stopping.

CVSS severity can’t keep up. Manual triage can’t keep up. The only scalable answer is exploit-probability scoring built into the tools your engineers already use.

Sample Output: KEV and EPSS Scoring Applied to 55 Real Dependabot Alerts

Headline result from the 2026-05-19 demo run (real repository, 55 open Dependabot alerts, k9 risk-scoring rubric 2026.05.18-v6):

55 alerts → 0 fix today, 0 to schedule, 55 to defer. No CVE in CISA KEV or VulnCheck KEV. No EPSS percentile above the 0.99 urgency floor. Reachability check landed on

  • code_not_loaded for 31
  • no_attacker_controlled_input for 18
  • unreachable_from_entrypoint for 4
  • zero undetermined

(Watch the 5-minute demo)

The details of one defer decision from that run:

CVE-2026-32871 — FastMCP OpenAPI provider, SSRF + path traversal

  • GHSA severity: Critical (CVSS 10.0). Would normally be a drop-everything fire.
  • KEV status: Not listed. No real-world exploitation evidence.
  • EPSS percentile: 0.309 (well below the 0.99 urgency floor).
  • Reachability: code_not_loaded. fastmcp is in the lockfile but not imported anywhere in the project, verified by grepping the source tree.
  • Verdict: DEFER. Bundle into the next routine dependency upgrade.
  • Forward-watch trigger: any new feature that imports fastmcp.server.openapi or wires a FastMCP server.

This is the false positive engineers hate: a Critical-severity alert for a vulnerability in a capability the app doesn’t even use. Reachable Risk gives your team the evidence to defer it without guesswork, and the trigger that flips the verdict if the situation changes.

Pricing

7-day free trial, then $10/month.

  • 100 findings included per month.
  • $0.25 per finding above plan.
  • Pay on a personal card. No procurement cycle.
  • Cancel anytime. No card required to start the trial.

If it doesn’t earn its keep in 7 days, walk away. No charge, nothing to cancel.

Running this for a whole team, or wiring into CI? That’s a separate package (Reachable Risk for Teams). Talk to us. We’re collecting interest while we validate the engineer experience first.

Score Your Real Backlog: MCP CVE Prioritization in Three Lines of Config

Add the MCP server to Claude Code, Codex, or a compatible agent. Three lines of config. If it earns its keep in 7 days, continue for $10/month. If not, walk away.

Start your 7-day free trial 
{
  "mcpServers": {
    "k9": {
          "type": "http",
          "url": "https://mcp.k9security.io/mcp"
        }
    }
}

Built for engineers who want their AI coding agent to triage real risk, not CVSS noise.