Skip to main content
Glama
vuln-intel-mcp

vuln-intel-mcp

by raulsidii

vuln-intel-mcp

CI License: MIT

A Model Context Protocol server that gives AI assistants such as Claude Desktop and Claude Code live vulnerability intelligence for triage. It pulls from NVD, FIRST EPSS and CISA KEV, then ranks CVEs with a transparent, risk-based priority score.

MCP in one line: an open protocol that lets an AI assistant call external tools and data sources through a standard interface. This server is one of those tools.

Why this exists: CVSS alone is not a priority

Scanners hand you hundreds of "CRITICAL" findings. CVSS measures how bad a bug could be, not how likely it is to be used against you. Patching by CVSS alone means spending most of the effort on bugs nobody exploits while real ones wait in the queue.

Three signals together give a much better answer:

Signal

Source

Question it answers

CVSS

NVD

How severe is the impact if exploited?

EPSS

FIRST.org

How likely is exploitation activity in the next 30 days? (a model's probability)

KEV

CISA

Is it already being exploited in the wild? (evidence)

In the live run below, three CVEs are all rated CVSS 9.1 to 9.8 CRITICAL. One of them (curl SOCKS5, CVE-2023-38545) has a 78% EPSS; the other two sit below 4%. CVSS treats them almost identically. This server doesn't.

Related MCP server: security-intel-mcp

Tools

Tool

Input

Returns

lookup_cve

cve_id, max_references? (default 10)

NVD description, CVSS v4.0 / v3.1 / v2 score + vector, CWE, status, dates, references

epss_score

cve_ids[] (1-100)

EPSS probability, percentile and model date per CVE

is_known_exploited

cve_ids[] (1-100)

KEV listing: date added, federal due date, required action, ransomware use

prioritize_cves

cve_ids[] (1-30)

Ranked table with tier, 0-100 score and a one-line rationale per CVE

search_cves

keyword, limit? (1-20, default 5), exact_match?

Matching CVE IDs with CVSS, publish date and summary

All tools are read-only (readOnlyHint: true). CVE IDs are validated and normalized (cve-2021-44228 works too).

Install

Requires Node.js 20 or newer to run (22.12+ to run the test suite).

git clone https://github.com/raulsidii/vuln-intel-mcp.git
cd vuln-intel-mcp
npm install
npm run build

Optional: NVD API key

Without a key, NVD allows 5 requests per 30 seconds; with one, 50. The server paces itself to stay under the limit, so a 20-CVE prioritize_cves call takes about two minutes without a key and a few seconds with one. Get a free key at https://nvd.nist.gov/developers/request-an-api-key and pass it as NVD_API_KEY.

Claude Code

claude mcp add vuln-intel -- node /absolute/path/to/vuln-intel-mcp/dist/index.js

# with an NVD API key, available in every project:
claude mcp add vuln-intel --scope user -e NVD_API_KEY=your-key -- node /absolute/path/to/vuln-intel-mcp/dist/index.js

Check it with claude mcp list, or /mcp inside a session.

Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "vuln-intel": {
      "command": "node",
      "args": ["/absolute/path/to/vuln-intel-mcp/dist/index.js"],
      "env": {
        "NVD_API_KEY": "optional-your-key"
      }
    }
  }
}

On Windows, use escaped backslashes or forward slashes in the path, e.g. "C:/Users/you/vuln-intel-mcp/dist/index.js". Restart Claude Desktop after saving.

Example conversation

The tool output below is real (captured on 2026-11-17 with npm run smoke). The assistant's wording is an example of what a client does with it.

User: Our scanner flagged these on the edge fleet: CVE-2023-38545, CVE-2024-45337, CVE-2021-44228, CVE-2024-24790, CVE-2024-3400. Four of them say CRITICAL. What do we fix first?

Assistant calls prioritize_cves with the five IDs:

#

CVE

Tier

Score

KEV

EPSS

CVSS

Rationale

1

CVE-2021-44228

CRITICAL

100.0

yes (ransomware)

99.9%

10.0 (v3.1)

Patch now — exploited in the wild: CISA KEV since 2021-12-10 (ransomware use), EPSS 99.9% (p100.0), CVSS 10.0 CRITICAL.

2

CVE-2024-3400

CRITICAL

100.0

yes (ransomware)

99.9%

10.0 (v3.1)

Patch now — exploited in the wild: CISA KEV since 2024-04-12 (ransomware use), EPSS 99.9% (p100.0), CVSS 10.0 CRITICAL.

3

CVE-2023-38545

HIGH

86.2

no

78.3%

9.8 (v3.1)

Patch soon — exploitation highly likely: not in KEV, EPSS 78.3% (p99.5), CVSS 9.8 CRITICAL.

4

CVE-2024-24790

MEDIUM

40.4

no

1.9%

9.8 (v3.1)

Schedule — severe on paper, but low exploitation likelihood: not in KEV, EPSS 1.9% (p80.6), CVSS 9.8 CRITICAL.

5

CVE-2024-45337

MEDIUM

38.7

no

3.7%

9.1 (v3.1)

Schedule — severe on paper, but low exploitation likelihood: not in KEV, EPSS 3.7% (p90.1), CVSS 9.1 CRITICAL.

Assistant: Two of these are emergencies, not just "critical":

  1. CVE-2021-44228 (Log4Shell) and CVE-2024-3400 (PAN-OS GlobalProtect) are both in CISA's Known Exploited Vulnerabilities catalog with known ransomware use. Patch or mitigate today, starting with whatever is internet-facing. The PAN-OS box is the perimeter itself, so if it's exposed, treat it as first and check for compromise, not just the patch.

  2. CVE-2023-38545 (curl SOCKS5 heap overflow) isn't in KEV, but EPSS puts it at 78% for exploitation activity in the next 30 days. Put it in this week's patch cycle.

  3. CVE-2024-24790 (Go net/netip) and CVE-2024-45337 (Go x/crypto/ssh misuse) score 9.8 and 9.1, but their EPSS is under 4%, and 45337 only bites if your code misuses PublicKeyCallback. Schedule them with the normal dependency bump.

Want me to pull the KEV required actions for the first two?

User: Yes, and show me the details on Log4Shell.

Assistant calls is_known_exploited with ["CVE-2021-44228", "CVE-2024-3400"] and lookup_cve with CVE-2021-44228, then summarizes the required actions, affected versions (2.0-beta9 through 2.15.0) and the CWE (CWE-917, expression-language injection).

Scoring formula

base  = 100 × (0.4 × CVSS/10 + 0.6 × EPSS)

score = 90 + base/10      if the CVE is in CISA KEV   → tier CRITICAL  (score 90-100)
score = base              otherwise                   → tier HIGH   if score ≥ 60
                                                        tier MEDIUM if score ≥ 35
                                                        tier LOW    if score < 35

Design choices:

  • KEV overrides everything. It is evidence of exploitation, not a prediction, so a KEV-listed CVE always ranks above any non-KEV CVE, no matter how high its CVSS or EPSS. CRITICAL is reserved for KEV.

  • EPSS weighs more than CVSS (60/40). Exploitation likelihood drives risk more than theoretical impact. A CVSS 10.0 with EPSS ≈ 0 lands at 40 (MEDIUM); a CVSS 6.0 with EPSS 0.9 lands at 78 (HIGH).

  • EPSS is used as a probability, not a percentile. Percentiles inflate small scores (a 2% EPSS is often above the 80th percentile). Percentiles are shown for context only.

  • CVSS v3.1 is preferred for scoring because nearly every CVE in NVD has one, so scores stay comparable across the list. v4.0 is used when v3.1 is missing, then v3.0, then v2. lookup_cve shows all of them.

  • Missing data is visible. No CVSS yet → assume 5.0; no EPSS → 0. Both are called out in the rationale, as are unreachable sources.

  • Ties break on EPSS, then CVSS, then CVE ID.

This is a triage aid, not a replacement for context. Asset exposure, compensating controls and business criticality still matter, which is exactly what the assistant can ask you about next.

Reliability

  • Rate limits: sliding-window pacing for NVD (5 or 50 requests / 30 s), plus exponential backoff with jitter on 403 / 429 / 5xx, honouring Retry-After.

  • Timeouts: 20 s per request (45 s for the 1.8 MB KEV feed), with up to 3 retries.

  • Caching: in-memory TTL cache. NVD and EPSS answers live for 6 h, the KEV catalog for 12 h. Concurrent KEV loads share one download.

  • Errors are tool results, not crashes: upstream failures come back as MCP tool errors (isError: true) with a readable message. prioritize_cves degrades gracefully: if one source is down it still ranks with the others and says what was missing.

  • Input validation: every argument is a zod schema; responses from all three APIs are validated before use.

Development

npm test           # vitest, offline: recorded API fixtures in test/fixtures
npm run typecheck  # tsc over src, tests and scripts
npm run build      # compile to dist/
npm run dev        # run the server from source with tsx
npm run smoke      # live check against the real APIs (needs network)
src/
  index.ts            stdio entry point
  server.ts           builds the McpServer and wires the clients
  config.ts           endpoints, timeouts, TTLs, limits
  scoring.ts          priority formula, tiers, rationale
  prioritize.ts       fan-out to the three sources with graceful degradation
  format.ts           Markdown rendering of tool output
  types.ts            domain types
  lib/                http (timeout + backoff), TTL cache, rate limiter, CVE ID validation
  sources/            NVD, EPSS and KEV clients and response parsers
  tools/              one file per MCP tool
test/                 unit + in-memory MCP integration tests, recorded fixtures
scripts/smoke.ts      live smoke test
===== lookup_cve {"cve_id":"CVE-2021-44228","max_references":3} [ok, 585 ms]

## CVE-2021-44228
**Status:** Analyzed · **Published:** 2021-12-10 · **Last modified:** 2026-08-11

- **CVSS v3.1:** 10.0 CRITICAL — `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H` (nvd@nist.gov, Primary)
- **CVSS v2.0:** 9.3 HIGH — `AV:N/AC:M/Au:N/C:C/I:C/A:C` (nvd@nist.gov, Primary)
- **CWE:** CWE-20, CWE-400, CWE-502, CWE-917

**Description:** Apache Log4j2 2.0-beta9 through 2.15.0 (excluding security releases 2.12.2, 2.12.3, and 2.3.1) JNDI features used in configuration, log messages, and parameters do not protect against attacker controlled LDAP and other JNDI related endpoints. An attacker who can control log messages or log message parameters can execute arbitrary code loaded from LDAP servers when message lookup substitution is enabled. From log4j 2.15.0, this behavior has been disabled by default. From version 2.16.0 (along with 2.12.2, 2.12.3, and 2.3.1), this functionality has been completely removed. Note that this vulnerability is specific to log4j-core and does not affect log4net, log4cxx, or other Apache Logging Services projects.

**References** (3 of 52):
- http://packetstormsecurity.com/files/165225/Apache-Log4j2-2.14.1-Remote-Code-Execution.html — Third Party Advisory, VDB Entry
- http://packetstormsecurity.com/files/165260/VMware-Security-Advisory-2021-0028.html — Third Party Advisory, VDB Entry
- http://packetstormsecurity.com/files/165261/Apache-Log4j2-2.14.1-Information-Disclosure.html — Exploit, Third Party Advisory, VDB Entry

Source: https://nvd.nist.gov/vuln/detail/CVE-2021-44228

===== epss_score {"cve_ids":["CVE-2021-44228"]} [ok, 119 ms]

| CVE | EPSS (30-day exploit probability) | Percentile | Model date |
|---|---|---|---|
| CVE-2021-44228 | 99.9% | p100.0 | 2026-11-16 |

EPSS = probability of exploitation activity in the next 30 days (FIRST.org). Percentile = share of all CVEs with a lower score.

===== is_known_exploited {"cve_ids":["CVE-2021-44228"]} [ok, 261 ms]

### CVE-2021-44228 — LISTED in CISA KEV
- **Name:** Apache Log4j2 Remote Code Execution Vulnerability
- **Vendor / product:** Apache / Log4j2
- **Date added:** 2021-12-10 · **Federal due date:** 2021-12-24
- **Known ransomware use:** Known
- **Required action:** For all affected software assets for which updates exist, the only acceptable remediation actions are: 1) Apply updates; OR 2) remove affected assets from agency networks. Temporary mitigations using one of the measures provided at https://www.cisa.gov/uscert/ed-22-02-apache-log4j-recommended-mitigation-measures are only acceptable until updates are available.
- **Summary:** Apache Log4j2 contains a vulnerability where JNDI features do not protect against attacker-controlled JNDI-related endpoints, allowing for remote code execution.

Catalog version 2026.11.13 (1781 entries). Absence from KEV is not proof that a CVE is unexploited.

===== prioritize_cves {"cve_ids":["CVE-2023-38545","CVE-2024-45337","CVE-2021-44228","CVE-2024-24790","CVE-2024-3400"]} [ok, 570 ms]

| # | CVE | Tier | Score | KEV | EPSS | CVSS | Rationale |
|---|---|---|---|---|---|---|---|
| 1 | CVE-2021-44228 | CRITICAL | 100.0 | yes (ransomware) | 99.9% | 10.0 (v3.1) | Patch now — exploited in the wild: CISA KEV since 2021-12-10 (ransomware use), EPSS 99.9% (p100.0), CVSS 10.0 CRITICAL. |
| 2 | CVE-2024-3400 | CRITICAL | 100.0 | yes (ransomware) | 99.9% | 10.0 (v3.1) | Patch now — exploited in the wild: CISA KEV since 2024-04-12 (ransomware use), EPSS 99.9% (p100.0), CVSS 10.0 CRITICAL. |
| 3 | CVE-2023-38545 | HIGH | 86.2 | no | 78.3% | 9.8 (v3.1) | Patch soon — exploitation highly likely: not in KEV, EPSS 78.3% (p99.5), CVSS 9.8 CRITICAL. |
| 4 | CVE-2024-24790 | MEDIUM | 40.4 | no | 1.9% | 9.8 (v3.1) | Schedule — severe on paper, but low exploitation likelihood: not in KEV, EPSS 1.9% (p80.6), CVSS 9.8 CRITICAL. |
| 5 | CVE-2024-45337 | MEDIUM | 38.7 | no | 3.7% | 9.1 (v3.1) | Schedule — severe on paper, but low exploitation likelihood: not in KEV, EPSS 3.7% (p90.1), CVSS 9.1 CRITICAL. |

Score = 100 × (0.4 × CVSS/10 + 0.6 × EPSS). KEV-listed CVEs are lifted to 90 + base/10 and always rank CRITICAL. Non-KEV tiers: HIGH ≥ 60, MEDIUM ≥ 35, LOW < 35.

===== search_cves {"keyword":"log4j jndi","limit":3} [ok, 29100 ms]

Showing 3 of 7 NVD results for "log4j jndi":

| CVE | CVSS | Published | Summary |
|---|---|---|---|
| CVE-2021-44228 | 10.0 (v3.1) | 2021-12-10 | Apache Log4j2 2.0-beta9 through 2.15.0 (excluding security releases 2.12.2, 2.12.3, and 2.3.1) JNDI features used in configuration, log messages, and parameters do not protect against attacker controlled LDAP and other… |
| CVE-2021-4104 | 7.5 (v3.1) | 2021-12-14 | JMSAppender in Log4j 1.2 is vulnerable to deserialization of untrusted data when the attacker has write access to the Log4j configuration. The attacker can provide TopicBindingName and TopicConnectionFactoryBindingName… |
| CVE-2021-45046 | 9.0 (v3.1) | 2021-12-14 | It was found that the fix to address CVE-2021-44228 in Apache Log4j 2.15.0 was incomplete in certain non-default configurations. This could allows attackers with control over Thread Context Map (MDC) input data when the… |

Refine the keywords or raise `limit` to see more.

The search_cves call took 29 s because it was the sixth NVD request in 30 s without an API key: the limiter waited instead of getting the client blocked.

Data sources and terms

License

MIT © Raül Silvero

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Provides live CVE data from NVD and EPSS without API key, enabling AI assistants to look up CVSS scores, search vulnerabilities, and check product CVEs.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides real-time vulnerability intelligence including CVE lookup, EPSS exploit probability, and CISA KEV status from free APIs, enabling AI assistants to prioritize CVEs by real-world risk.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to look up CVE details, EPSS exploit probability, and CISA KEV status from free public APIs to prioritize vulnerabilities by real-world risk. Combines these sources into a single enriched, prioritized view using a KEV > EPSS > CVSS rule.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to search, correlate, and monitor real-time vulnerability intelligence from NVD, CISA KEV, EPSS, and MITRE ATT&CK, including CVE details, critical CVE tracking, known exploited vulnerabilities, and exploitation probability scores.
      5
      2
      MIT