Fleet demo video pipeline — narrated walkthroughs synced to true speech length, with real background music, sound effects, and page transitions (Playwright, speech-mcp, songgeneration-mcp, sfx-mcp, vfx-mcp, FFmpeg)
- capability exposure inferred + 22
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 2d ago · see ecosystem CVEs →
- A · 3 → B · 19
- A · 0 → A · 3
- A · 3 → A · 0
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 0b6da17 · analyzer v33 · 2d ago
skills & prompt files 6
- agent-rules sandraschi-demo-vid-mcp-0b6da17/.cursorrules
- agent-rules sandraschi-demo-vid-mcp-0b6da17/.github/copilot-instructions.md
- skill sandraschi-demo-vid-mcp-0b6da17/.opencode/skills/session-context/SKILL.md
- agent-rules sandraschi-demo-vid-mcp-0b6da17/.windsurfrules
- agent-rules sandraschi-demo-vid-mcp-0b6da17/AGENTS.md
- agent-rules sandraschi-demo-vid-mcp-0b6da17/CLAUDE.md
[](https://mcpobservatory.com/servers/github:sandraschi/demo-vid-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of sandraschi.