vulnerable.now
Free CVE lookups, lockfile checks and patch-priority ranking for AI agents
- Pricing
- Free
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 0.6.0
- Listing updated
- 3 days ago
About vulnerable.now
vulnerable.now is a free MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.
Each vulnerability gets one merged entry drawn from the CVE List, NVD, the GitHub Advisory Database, OSV, ENISA's EUVD, CISA KEV, FIRST EPSS, Exploit-DB, Metasploit, Nuclei and VulnCheck KEV. An entry carries the CVSS score, KEV status, EPSS estimate, public exploits, detection templates and fixed versions. The catalogue syncs every 15 minutes, with KEV checked hourly.
Through the MCP server an agent can look up or search CVEs, list what was recently published or exploited, rank what to patch, and check lockfiles, SBOMs and website technologies. The priority score runs from 0 to 100: evidence of exploitation counts for up to 40 points, EPSS percentile up to 20, CVSS up to 30 and automatability up to 10.
The site states there is no account, API key or paid tier, and that the same data is also available as RSS, Atom, JSON Feed and a JSON API. In the web checker, lockfiles are read in the browser and only package names and versions are sent. A clean result only means no published advisory matches those versions.
Install
Run in a terminal
claude mcp add --transport http mcp https://vulnerable.now/mcpAdd to Settings → Connectors → Add custom connector
https://vulnerable.now/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://vulnerable.now/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://vulnerable.now/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"serverUrl": "https://vulnerable.now/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://vulnerable.now/mcp"
}
}
}Tools this server provides (9)
Read directly from the server.
- get_vulnerability
- Get the merged entry for one or more IDs: CVE, GitHub advisory (GHSA), EUVD, or an OSV ID such as PYSEC, GO or RUSTSEC. Returns the description, CVSS, CISA KEV status, EPSS, public exploits, affected packages, fixed versions, priority and source links.
- get_poc
- List the public exploit code and proofs of concept the sources link to one vulnerability: Metasploit exploit modules, Exploit-DB entries, references NVD or the CNA tagged as exploits (broken links left out), and GitHub PoC repositories (most stars first). Links only; nothing is downloaded or run. The same JSON as GET /api/v1/entries/{id}/pocs. GitHub PoCs and tagged references are unverified third
- get_overview
- Get the stored AI-written overview of one CVE: one paragraph on what the flaw is, what it affects, what an attacker can do, whether it is exploited and how to fix it, written by Hinoki Offensive One from the entry's source data. Overviews are written only when someone opens the CVE page on vulnerable.now, so this tool reads and never writes one. status says whether the paragraph is ready, stale (t
- search
- Search the whole catalog by words: product, vendor, package, CVE ID, common vulnerability name, research metadata or description text. Best match first by default. Each result says which fields matched. When nothing matches, the reply suggests a broader query.
- get_package
- Every known vulnerability in one open source package, most urgent first, with the affected ranges and fixed versions published for that package. Give a version to learn which advisories affect it and the lowest upgrade that leaves every affecting range.
- get_product
- Every known vulnerability in one vendor product, such as an operating system, browser, server, CMS or appliance, most urgent first, with the affected versions and fixes. The vendor is optional: with only a product name, a clear match is answered directly and otherwise the candidates are listed. Give a version to learn which entries affect it and the lowest upgrade that clears them.
- list_feed
- List vulnerabilities newest first (KEV listings by date added when kev is set). Filter by severity, CISA KEV, exploitation, public exploit code, fix availability, ecosystem, vendor, product, text and dates. Use modified_since to pick up changes since a previous run.
- top_priority
- What to patch first: the vulnerabilities with the highest priority score (exploitation, EPSS, CVSS, automatability) among those with activity in a time window, optionally narrowed to an ecosystem, vendor or product.
- check_stack
- Find known vulnerabilities in what a project or site runs, ranked by what to fix first. Send exact package versions, the raw content of a lockfile (package-lock.json, poetry.lock, go.sum and others), a CycloneDX or SPDX SBOM, a Wappalyzer export, or detected technologies such as nginx 1.18.0. Returns each finding with severity, exploitation, priority and fixed versions.
What it does
- Merged CVE entries
- One record per vulnerability combining many public advisory and exploit sources.
- Exploitation evidence
- Shows CISA KEV status, EPSS, public exploits and detection templates.
- Patch priority score
- A 0 to 100 score for ordering a patch queue.
- Dependency checks
- Checks lockfiles, SBOMs and Wappalyzer exports for known vulnerabilities.
- Fixed versions
- Lists the version that fixes each known issue where available.
- Open feeds and API
- RSS, Atom, JSON Feed and a JSON API alongside the MCP server.
Good for
- Ask an agent which new CVEs are being exploited this week
- Decide which dependency upgrades to do first
- Check a project's lockfile for known vulnerabilities
- Look up whether a CVE has a public exploit or Nuclei template
- Subscribe a team channel to critical CVEs for one ecosystem
Pricing
Free
No account, API key or paid tier
Prices change. Check vulnerable.now before you buy.
vulnerable.now FAQ
Does it need an account or API key?
No. The MCP endpoint at https://vulnerable.now/mcp needs no authentication.
How fresh is the data?
The catalogue syncs every 15 minutes; CISA KEV is hourly and several exploit sources every six hours.
How is severity decided?
From the CVSS base score, using NVD's score first, then those from the CNA, CISA, GitHub and ENISA.
Does a clean lockfile check mean my project is safe?
No. It only means no published advisory matches those exact versions.
Is vulnerable.now free?
Yes. vulnerable.now is free to use.
How do I add vulnerable.now to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp https://vulnerable.now/mcp
What are the best alternatives to vulnerable.now?
The closest alternatives to vulnerable.now are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.
Alternatives to vulnerable.now

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools
Agent Roast
MCP serverOffline review that flags agent changes which weaken tests, assertions or CI
Runs locally- Open source
- 4 Hacker News points
- Developer tools

Midplane
MCP serverPostgres gateway for AI agents with table grants, column masking and approval for writes
Runs locally- Open source
- 5 GitHub stars
- Databases

Leash
MCP serverReview what your AI touched, approve risky actions and undo supported changes
- 1 tool
- Remote
- Free
- 1 GitHub star
- Security
Zero-log MCP server with 49 tools for AI guardrails, secret scanning and EU compliance
- 49 tools
- Remote
- Freemium
- Security

SecureCloud
MCP serverSentinelOne and IT security catalog, prices, quotes and checkout links for Israel
- 7 tools
- Remote
- Free
- Security