Tiling IDE for macOS to manage multiple Claude Code sessions in parallel
- capability exposure inferred + 35
- tool safety inferred + 14
inferred
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 10h ago · see ecosystem CVEs →
- C · 37 → C · 49
- B · 34 → C · 37
- B · 32 → B · 34
- A · 0 → B · 32
No known CVEs for this server.
- high tool shadowing terminal_resize
tool "terminal_resize" shadows a verified server's tool
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 7ee9c31 · analyzer v33 · 1w ago
skills & prompt files 3
- agent-rules roman10-mcode-7ee9c31/.claude/commands/mcode-release.md
- agent-rules roman10-mcode-7ee9c31/.github/copilot-instructions.md
- agent-rules roman10-mcode-7ee9c31/CLAUDE.md
[](https://mcpobservatory.com/servers/github:roman10/mcode/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 roman10.