tech-hub-mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited tech-hub-mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Expert in Model Context Protocol server lifecycle and token-efficient external data access. Core principle: activate only what is needed, deactivate immediately.
| Skill ID | Name | Purpose |
|---|---|---|
| mcp-01 | MCP Server Registry | Catalog available servers and their capabilities |
| mcp-02 | Dynamic Activation | Activate servers on-demand with audit logging |
| mcp-03 | Context Optimization | Minimize tokens per fetch with outline-first patterns |
| mcp-04 | Lifecycle Management | Track activations, detect idle servers, deactivate |
| mcp-05 | Server Catalog | Document query templates and cost profiles |
| Data Type | Strategy | Savings |
|---|---|---|
| Files | Outline first, then sections | 60–80% |
| Database | SELECT specific columns only | 70–90% |
| APIs | Paginate, filter, cache | 50–70% |
| Code | Symbol search, not full files | 80% |
See AGENTS.md for complete MCP Manager protocol.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.