Guard Mail

# Secure email inbox protected against prompt injection attempts, malware, viruses and more This MCP server acts as a secure gateway between your AI agents and email systems, protecting against common email-borne threats before content ever reaches your LLM. Every message is scanned for prompt injection attempts, malware, viruses, spam, and other malicious content, ensuring your agents only process trusted, sanitized emails. ## Features * **Prompt Injection Protection** – Detects and neutralizes prompt injection attacks embedded in email content. * **Malware & Virus Scanning** – Prevents AI agents from processing malicious attachments and infected messages. * **Spam & Phishing Detection** – Filters unwanted and deceptive emails before they reach your workflows. * **Secure MCP Integration** – Connect AI agents through the Model Context Protocol (MCP) for controlled, secure email access. * **Safe Email Processing** – Delivers clean, validated email content while blocking or quarantining suspicious messages. * **Enterprise Ready** – Designed for AI-powered automation, customer support, assistants, and autonomous workflows. ## Ideal For * AI customer support agents * Email automation workflows * Autonomous assistants * Enterprise AI applications * Security-conscious MCP deployments Keep your AI productive while ensuring email remains a trusted source of information.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://mail-guard--afluffysquirrel.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "Guard Mail": {
      "url": "https://mail-guard--afluffysquirrel.run.tools"
    }
  }
}

能力清单

工具	说明
register_user	Register a new Guardmail user and provision a custom email address.
send_email	Send an email from the user's custom Guardmail address with automatic LLM Guard and ClamAV attachment scanning.
list_inbox	List inbox emails with security scan results.
list_spam	List emails flagged as spam by the spam filter.
list_quarantine	List emails quarantined by LLM Guard or ClamAV.
search_emails	Search the authenticated user's mailbox by subject and/or body text, optionally narrowed by a received-at date range and/or a status folder. Provide at least one of subject, body, since, or until. All filters combine with AND; matches are case-insensitive. Text matching uses SQL LIKE wildcards: `%` matches any sequence of characters and `_` matches any single character. These are interpreted as wildcards, not literals — e.g. `50%` also matches `500`, and `order_7` also matches `orderx7`. There is no regex support. Results are newest-first and paginated, with the same security scan metadata and MCP redaction rules as list_inbox.
get_email	Get full email details including the complete security scan report.
move_to_inbox	Manually move a quarantined or spam email back into the inbox. Use this when a user confirms an email was quarantined or flagged as spam in error and wants to retrieve it. The original security scan results are preserved — if LLM Guard or ClamAV flagged the email, its content stays redacted for MCP consumers after the move, but the user can read it in the web UI. Only emails currently in "quarantine" or "spam" can be moved; inbox/pending/scanning/sent emails cannot.
update_spam_settings	Update the user's spam filter configuration (rules, allow/block lists, sensitivity).
update_security_settings	Update the user’s security settings. Currently controls whether outbound (sent) emails are scanned by LLM Guard for prompt injection and toxicity before delivery. Inbound scanning is always on regardless of this setting.
get_quota	Get the authenticated user’s subscription tier and email quota usage: monthly/daily limits, how many emails (sent + received) have been used this month and today, and whether the account email is verified. Use this before sending a batch of emails to check remaining quota, or to tell the user which plan they are on and whether they need to verify their email or upgrade to send more.
get_attachment_url	Mint a short-lived signed download URL for an attachment on an email the caller owns. Use this to fetch attachment bytes (e.g. to read a document or image the user sent/received). The returned URL is fetchable with a plain GET — no auth header needed — and expires after a few minutes; request a fresh URL if it has expired. Attachments flagged as malware by ClamAV are removed at scan time and cannot be downloaded.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。