Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers
- capability exposure inferred + 16
- tool safety inferred + 5
- trust mitigators mixed − 8
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 1w ago · see ecosystem CVEs →
- B · 25 → A · 13
- A · 8 → B · 25
- A · 0 → A · 8
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed commit 6d9bdc7 · analyzer v33 · 4d ago
skills & prompt files 5
- agent-rules modelcontextprotocol-ext-apps-6d9bdc7/AGENTS.md
- skill modelcontextprotocol-ext-apps-6d9bdc7/plugins/mcp-apps/skills/add-app-to-server/SKILL.md
- skill modelcontextprotocol-ext-apps-6d9bdc7/plugins/mcp-apps/skills/convert-web-app/SKILL.md
- skill modelcontextprotocol-ext-apps-6d9bdc7/plugins/mcp-apps/skills/create-mcp-app/SKILL.md
- skill modelcontextprotocol-ext-apps-6d9bdc7/plugins/mcp-apps/skills/migrate-oai-app/SKILL.md
danger signals2
- dynamic code execution new Function() modelcontextprotocol-ext-apps-6d9bdc7/examples/threejs-server/src/threejs-app.tsx :182
const fn = new Function( - suspicious endpoint 169.254.169.254 (cloud metadata) modelcontextprotocol-ext-apps-6d9bdc7/examples/pdf-server/server.test.ts :549
expect(validateUrl("http://169.254.169.254/").valid).toBe(false);
[](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.