github scanned Safe content atomic container

lighthouse

把本地项目开成一扇受治理的 MCP 窗口给 AI 读:四道闸 + 出口脱敏 + 全程审计 + 写开关 + 提权审批,选择权交给用户;不买域名也能用(本机 / 局域网 IP / 免费隧道)。| Turn a local project into a governed MCP window for AI: four gates, egress redaction, audit, write switch, owner-approved elevation; no domain purchase needed (local / LAN IP / free tunnels).

Cognium trust score
57%
Tier
Scanned

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 2026-09-28.

Scan details: Circle-IR · 2026-09-28 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
container
Source
GitHub
Author type
human
Last scanned
2026-09-28
Updated
2026-09-28
View source Find related skills

Use via MCP

MCP

Resolve lighthouse 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
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry