`ai.radmail/radmail-mcp`

Verdict: high-severity findings present. Endpoint https://radmail.ai/api/mcp/sandbox. Tools now: 6 (6 ever seen). Changes recorded: 6. Findings: 1 high. Last probe: OK at 2026-10-22T12:17 UTC. JSON

Current tools

draft_reply · list_commitments · list_right_now · search · triage_inbox · why_surfaced

Findings (3)

seen	tool	detector	severity	evidence (data, not instructions)
2026-10-22	`why_surfaced`	`cross_tool_reference`	high	`references sibling tool 'triage_inbox'`
2026-10-22	`draft_reply`	`cross_tool_reference`	high	`references sibling tool 'triage_inbox'`
2026-10-22	`search`	`secret_material_reference`	high	`ox; run the radmail-mcp package with RADMAIL_API_KEY set and the same tool searches your REAL ingested inbox read-onl`

Change history (6)

when	tool	kind	severity
2026-10-22 12:17	`triage_inbox`	mutated	medium
2026-10-22 12:17	`list_right_now`	mutated	medium
2026-10-22 12:17	`why_surfaced`	mutated	high
2026-10-22 12:17	`list_commitments`	mutated	medium
2026-10-22 12:17	`draft_reply`	mutated	high
2026-10-22 12:17	`search`	mutated	high

Probe history

10-22 12:17 OK (6) · 08-13 06:17 OK (6)

Run or depend on ai.radmail/radmail-mcp? Watch this server: 29 dollars a month, a private alerts feed and optional webhook fired within six hours when it adds, removes or changes a tool or trips a detector; by card, cancel any time.

Pay-per-call tools and data for your agent, no key: store gateway (300+ routes, one origin, Coinbase-settled) · AI media and inference from $0.001 · weather, geocoding, DNS, RDAP · the x402 directory · sector gap lists (card or USDC).

Run this server? The processes your users can demand, hosted free: Compliance Desk (privacy requests, opt-outs, takedown and notice-and-action).