Email verification for AI agents: send, hold or kill with the reason. CLI, MCP server and hosted API.
- capability exposure inferred + 10
- tool safety inferred + 12
- 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.
grade last moved 6d ago · see ecosystem CVEs →
No known CVEs for this server.
- high dangerous code
credential logged in 1 file(s)
analyzed commit b6d6bc0 · analyzer v33 · 6d ago
danger signals3
- suspicious endpoint api.telegram.org andrewchmr-mxprobe-b6d6bc0/server/src/notify.ts :39
const res = await fetchImpl(`https://api.telegram.org/bot${tgToken}/sendMessage`, { - suspicious endpoint api.telegram.org andrewchmr-mxprobe-b6d6bc0/server/test/notify.test.ts :42
assert.equal(r.calls[0]?.url, "https://api.telegram.org/bottok/sendMessage"); - credential in logs credential in log andrewchmr-mxprobe-b6d6bc0/server/src/index.ts :43
console.info(`mxprobe-server ${VERSION} on http://${HOST}:${PORT} db=${DB_PATH} telegram=${notifier.configured.telegram} email=${notifier.configured.email} stripe=${!!(env.STRIPE_SECRET_KEY && env.STR
[](https://mcpobservatory.com/servers/github:andrewchmr/mxprobe/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 andrewchmr.