Patchfirst
Server Details
Exploited CVEs ranked by what to patch first, with CISA KEV, EPSS and ATT&CK evidence.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Each tool has a clear anchor: check_stack takes packages, get_vulnerability takes a single CVE id, list_feed is recency-ordered, list_exploited is KEV-ranked, and the two ATT&CK tools are explicit inverses of one another. The only mild overlap is among search / list_feed / list_exploited, which all enumerate CVEs, but their ordering and filter semantics distinguish them well enough.
Three conventions coexist: verb_noun (check_stack, list_exploited, list_feed, get_vulnerability), a bare verb (search), and a noun_for_noun pair (cves_for_technique, techniques_for_cve). The *_for_* pair is internally consistent and the names remain readable, but the set does not follow a single predictable pattern.
Seven tools is a tight, well-scoped surface for a vulnerability-intelligence lookup service, with no obvious filler. Each tool maps to a distinct query pattern an agent would actually need.
The surface covers the core lifecycle of vulnerability triage: batch package checking, free-text discovery, recency feed, exploited ranking, per-CVE detail, and ATT&CK traversal in both directions. Minor gaps exist — no structured vendor/product facet browsing, no SBOM/file ingestion, and no way to look up technique metadata or list all techniques/tactics.
Available Tools
7 toolscheck_stackCheck stackARead-onlyIdempotentInspect
Check a list of packages for known vulnerabilities via OSV.dev, then join with Patchfirst exploitation data (CISA KEV, EPSS, priority, ATT&CK techniques). Results are sorted exploited-first so you fix what attackers actually use. Ecosystems use OSV names: npm, PyPI, Maven, Go, crates.io, RubyGems, NuGet, Packagist, Debian, Alpine, etc.
Inputs: packages (required).
cves_for_techniqueCVEs for techniqueARead-onlyIdempotentInspect
Reverse ATT&CK lookup: which CVEs lead to a given technique, e.g. "which exploited CVEs give T1190 Exploit Public-Facing Application?". Sorted by Patchfirst priority. Parent ids include sub-techniques (T1059 matches T1059.004). Each hit shows the link's provenance badge and best evidence quote.
Inputs: technique_id (required), limit, kev_only, include_subtechniques.
get_vulnerabilityGet vulnerabilityARead-onlyIdempotentInspect
Full Patchfirst record for one CVE: description, CVSS, EPSS, CISA KEV status, the ATT&CK techniques attackers use with it (each with provenance badge, basis, evidence quotes and report links), threat reports that name it, and the priority score with its factors. Every field carries provenance and a source URL.
Inputs: cve_id (required).
list_exploitedList exploited CVEsARead-onlyIdempotentInspect
Top known-exploited CVEs (CISA KEV) ranked by Patchfirst priority, optionally filtered to known ransomware use, an ATT&CK tactic (e.g. "initial-access", "Privilege Escalation", "TA0004") or a technique id. Each result lists its techniques with provenance badges.
Inputs: limit, tactic, technique, ransomware_only.
list_feedNewest CVEsARead-onlyIdempotentInspect
Newest CVEs by published date, with KEV/EPSS/CVSS (source data) and priority. Complete for the last 30 days (every CVE published in that window is core tier); older dates list core-tier CVEs only. Filter by a since-date and minimum CVSS severity.
Inputs: limit, since, min_severity.
searchSearch CVEsARead-onlyIdempotentInspect
Search every published CVE (all tiers) by CVE id (full or partial, e.g. "CVE-2024-3400", "2024-34"), vendor, product or title words (e.g. "fortinet fortios", "confluence", "sql injection"). Ranked by match quality, then priority.
Inputs: query (required), limit.
techniques_for_cveTechniques for CVEARead-onlyIdempotentInspect
What attackers do with a CVE: its MITRE ATT&CK techniques grouped by tactic in kill-chain order (Reconnaissance -> Impact). Each technique lists every supporting link with provenance badge, basis, evidence quote and report URL, strongest provenance first.
Inputs: cve_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Rank CVEs by real exploitation signals from CISA KEV and EPSS, and get alerts on your products.
CISA KEV status and EPSS scores for CVE IDs, ranked P1/P2/P3 for patching, via Apify.
Is a CVE exploited? CISA KEV, FIRST EPSS, CVSS and SSVC with a patch-first verdict. Free, no key.
Daily CVE priorities ranked by real exploitation (KEV+EPSS) for AI agents; free teaser, paid full
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables prioritizing vulnerabilities by real-world exploitation evidence, combining CISA KEV, EPSS, CVSS, and SSVC to rank CVEs and package versions, and providing fix recommendations.42MIT
- AlicenseNot gradedqualityDmaintenanceEnables CVE lookups and risk assessment by integrating CISA Known Exploited Vulnerabilities (KEV) data and CVSS metrics. It helps users prioritize patching efforts by ranking vulnerabilities based on exploitation status and calculated risk scores.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to pull live NVD details, FIRST EPSS probabilities and CISA KEV status for CVEs, then rank a set of them into prioritized tiers with a transparent 0-100 risk score and a one-line rationale each. Also supports keyword searching and graceful degradation when a source is unavailable, so triage conversations can move from hundreds of scanner findings to a defensible patch order.MIT
- AlicenseNot gradedqualityDmaintenanceEnables 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
Glama MCP Gateway
Add one secure layer between your agents and this server.