The request names the cvss-score-extraction skill, which is indexed from BenchFlow's SkillsBench catalog 111. For direct CVSS retrieval from NVD or CVE data, ContrastCyber's CVE lookup and CVSS parsing actions 212 and Casey Hand's NVD tools 313 are the closest matches.
- 1
- 2
ContrastCybercontrastcyber.comverified and signed
Its CVE Lookup action returns CVE details including CVSS v3.1 and v2 scores and vectors 212, and get_cvss_details parses a CVSS v3.x vector into a per-metric breakdown with a recomputed base score 212.
official:MCP server · ContrastAPI
for agents: get_cvss_details · cve_lookup · CVE Lookup
- 3
Sources
- 1BenchFlow — A frontier environment lab for AI agentsbenchflow.ai · read 2026-10-30
- 2ContrastCyber Products for Humans and AI Agentscontrastcyber.com · read 2026-10-29
- 3Casey Hand · Software Engineer, AI Infrastructurecaseyjhand.com · read 2026-10-29
- 11cvss-score-extraction: declares "cvss-score-extraction" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12ContrastAPI: declares "get_cvss_details" (the record we read and signed)unfragile.ai · read 2026-10-24
- 13nist-nvd-mcp-server: declares "nvd_get_cve" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
cvss-score-extraction · cvss-score-extraction verified and signed
Extract CVSS (Common Vulnerability Scoring System) scores from vulnerability data sources with proper fallback handling. This skill covers understanding CVSS v3, handling multiple score sources (NVD, GHSA, RedHat), implementing source priority logic, and dealing with missing scores in security repor
get_cvss_details · ContrastAPI verified and signed
Parse a CVSS v3.x vector string into a per-metric breakdown plus a recomputed base score. Returns the canonicalized vector, version (3.0 or 3.1), base_score, base_severity (NONE/LOW/MEDIUM/HIGH/CRITICAL), and the eight base metrics: attack_vector (NETWORK/ADJACENT_NETWORK/LOCAL/PHYSICAL), attack_com
nvd_get_cve · nist-nvd-mcp-server verified and signed
Fetch one or more CVEs by ID from the NIST National Vulnerability Database. Returns CVSS scores across all available versions (v2.0, v3.0, v3.1, v4.0), CWE weakness classifications, affected CPE configurations, CISA KEV fields, and references. Up to 100 CVE IDs per call. For bulk lookups of more tha
load_rapid7_parquet · Rapid7 Bulk Export MCP Server found in code, not yet checked
Load vulnerability data from existing Parquet file(s).
extract-structured-data · OpenAI (Activepieces) verified and signed
Extract Structured Data — Pull the fields you define out of a block of text.
epss_score_lookup · vulnerability-intelligence-mcp found in code, not yet checked
Look up EPSS exploit prediction scores for one or more CVEs (comma-separated). If any CVEs are on your watchlist, score changes since last check are included.
ossf/scorecard-action · OSSF Scorecard action verified and signed
Run OSSF Scorecard checks and output results in SARIF, JSON, or in-toto format
extract · Firecrawl (Activepieces) verified and signed
Extract Structured Data — Extract structured data from multiple URLs using AI.
HasData · HasData Documentation verified and signed
Use when scraping web pages, searching Google SERP, extracting data
· VisiData website read, tools not yet checked
Command-line interactive multitool for tabular data.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.