Loading…
Email OS for agents, providing real-inbox search, triage, commitment tracking, and a verifiable BEC hard-stop.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The radmail-sandbox MCP server exposes 6 tools, focused primarily on general-purpose capabilities. Its published description reads: "Email OS for agents, providing real-inbox search, triage, commitment tracking, and a verifiable BEC hard-stop". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates radmail-sandbox D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check radmail-sandbox's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add radmail-sandbox to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://radmail.ai/api/mcp/sandboxStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Rank a mailbox on two axes (importance x urgency) and return what needs a human now versus what can wait or is already handled — with each thread's open commitment (the promise you owe or are owed, an
Return only the 'Right Now' lane — the most recent and most important messages that genuinely can't be missed.
Explain in plain English why a given message was surfaced — the signals (sender, urgency, commitment) behind its rank.
Extract the open commitments in the correspondence, both owed by you and owed to you, with who and by-when.
Draft a reply for a thread. It returns text for a human to review — it does not and cannot send it.
Find a specific message by sender, subject, or content. Results come back most-relevant + newest first, and every hit says where it matched (from / subject / body) and why. On this hosted sandbox it s
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
emory, free, no credentials), but it is the sandbox engine — not the producRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
y read, triage, search, draft, and read-only diagnostic tools. There iRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: draft_reply
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "draft_reply"RecommendationScope tools to the minimum needed.
tool: search
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "search"RecommendationScope tools to the minimum needed.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.
Access Vonage API documentation, code snippets, tutorials, and troubleshooting resources.