Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers
- capability exposureinferred+16
- trust mitigatorsmixed−8
inferredmixed
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.
graded 14m ago · see ecosystem CVEs →
- A · 0 → A · 8
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 ca1d298 · analyzer v17 · 2d ago
skills & prompt files 5
- agent-rulesmodelcontextprotocol-ext-apps-ca1d298/AGENTS.md
- skillmodelcontextprotocol-ext-apps-ca1d298/plugins/mcp-apps/skills/add-app-to-server/SKILL.md
- skillmodelcontextprotocol-ext-apps-ca1d298/plugins/mcp-apps/skills/convert-web-app/SKILL.md
- skillmodelcontextprotocol-ext-apps-ca1d298/plugins/mcp-apps/skills/create-mcp-app/SKILL.md
- skillmodelcontextprotocol-ext-apps-ca1d298/plugins/mcp-apps/skills/migrate-oai-app/SKILL.md
[](https://mcpobservatory.com/servers/github:modelcontextprotocol/ext-apps/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 modelcontextprotocol.