Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite
- capability exposure inferred + 35
- tool safety inferred + 14
- trust mitigators mixed − 5
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 →
- C · 42 → C · 44
- C · 39 → C · 42
- C · 44 → C · 39
- A · 0 → C · 44
No known CVEs for this server.
- high dangerous code
dynamic exec: eval()/exec() · suspicious bundled script in 11 file(s)
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit ac4966c · analyzer v33 · 1w ago
skills & prompt files 2
danger signals12
- dynamic code execution eval()/exec() Dicklesworthstone-mcp_agent_mail-ac4966c/tests/test_guard_worktrees.py :881
exec( # deliberately running the rendered hook under test - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/automatically_detect_all_installed_coding_agents_and_install_mcp_agent_mail_in_all.sh :57
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/install.sh :58
curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/mcp_agent_mail/main/scripts/install.sh | bash -s -- --yes - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_claude_code.sh :35
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_cline.sh :36
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_codex_cli.sh :34
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_cursor.sh :33
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_factory_droid.sh :33
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_gemini_cli.sh :33
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_github_copilot.sh :39
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_opencode.sh :38
eval "$(uv run python - <<'PY' - suspicious bundled script suspicious bundled script Dicklesworthstone-mcp_agent_mail-ac4966c/scripts/integrate_windsurf.sh :36
eval "$(uv run python - <<'PY'
[](https://mcpobservatory.com/servers/github:Dicklesworthstone/mcp_agent_mail/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 Dicklesworthstone.