Security Intel MCP
為AI代理提供的威脅情報：CVE查詢（NVD + CISA KEV）、套件漏洞檢查（OSV）、惡意URL偵測（URLhaus）及IP信譽評估（AbuseIPDB）。
文件
Security Intel MCP — by SelfLabbs
Vulnerability intelligence for AI agents — as MCP tools your agent can call mid-task. No API keys.
Tools
| Tool | What it does | Source |
|---|---|---|
cve_lookup | CVE summary: description, CVSS score & severity, CWE, references | NVD (NIST) |
package_vulnerabilities | Known vulnerabilities for a package/version | OSV.dev |
audit_dependencies | Audit a whole package.json (or dependency list) in one call | OSV.dev |
No API keys required for any tool.
Quick start
claude mcp add --transport http security-intel https://security.selflabbs.com/mcp
Or point any MCP client at https://security.selflabbs.com/mcp.
Data & attribution
Vulnerability data comes from the National Vulnerability Database (NIST — US public domain) and OSV.dev (CC-BY 4.0), the same open source used by scanners like Trivy and Grype.
Part of SelfLabbs — keyless intelligence APIs for AI agents.