EPSS (Exploit Prediction Scoring System)
The EPSS MCP server provides AI assistants with access to vulnerability intelligence by integrating data from the NVD API and EPSS scoring system. Developed by Jerry Gamblin, this implementation fetches detailed CVE information including descriptions, CWEs, CVSS scores, and EPSS percentiles that indicate exploitation likelihood within 30 days. The server supports deployment via Docker for Open-WebUI integration or direct connection to VS Code through the Microsoft Copilot Labs extension, making it valuable for cybersecurity professionals who need to prioritize vulnerability remediation efforts based on exploitation probability without switching contexts.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/jgamblin/epss-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve EPSS (Exploit Prediction Scoring System) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.