Compliance & verification toolkit for AI agents — OFAC sanctions screen, KYA, transaction risk + disposable email/SMS inboxes. MCP + HTTP + CLI.
- capability exposure inferred + 32
- 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.
graded 2m ago · see ecosystem CVEs →
- B · 32 → B · 29
- B · 29 → B · 32
- A · 0 → B · 29
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 e4476ce · analyzer v28 · 1w ago
skills & prompt files 1
- agent-rules kindrat86-agentmail-e4476ce/CLAUDE.md
danger signals3
- suspicious endpoint eu.i.posthog.com (telemetry)
expected for this server's purpose
kindrat86-agentmail-e4476ce/api.py :82
" script-src 'self' 'unsafe-inline' https://eu.i.posthog.com https://js.stripe.com{extra_script};" - suspicious endpoint eu.i.posthog.com (telemetry)
expected for this server's purpose
kindrat86-agentmail-e4476ce/scripts/build_programs_pseo.py :63
'{api_host:"https://eu.i.posthog.com",person_profiles:"identified_only"})</script>') - suspicious endpoint eu.i.posthog.com (telemetry)
expected for this server's purpose
kindrat86-agentmail-e4476ce/scripts/build_pseo_round20.py :77
'{api_host:"https://eu.i.posthog.com",person_profiles:"identified_only"})</script>')
[](https://mcpobservatory.com/servers/github:kindrat86/agentmail/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 kindrat86.